Page 1
1 1
QUANTITATIVE RESEARCH – NATURE,
CHARACTERISTICS, SIGNIFICANCE,
CRITIQUE
Unit structure :
1.0 Objectives
1.1 Introduction
1.2 Nature
1.3 Characteristics
1.4 Significance
1.5 Critique
1.6 Summary
1.7 Questions
1.8 References and Further Readings
1.0. OBJE CTIVES:
To familiarize students with nature of quantitative research
To explain its characteristics and significance along with its critiques
1.1 INTRODUCTION:
Quantitative research is a systematic approach to collect information via
samplingmethods, for i nstance, questionnaires, online polls and online
surveys. It is gathered from both potential and existing subjects an d
depicted in terms of numerics .
Quantitative research is generally used in fields like political science,
gender studies,community health, marketing, sociology, economics,
psychology, demography, andeducation. Its objective is to employ
mathematical theories in relation to phenomena. The process offers a
connection between mathematical expression and empirical observation.
Quantitative resea rch is a method to measure variables, analyze them and
reportrelationships amongst the studied variables through a numerical
system. Its objective is to understand, analyze, describe and make future
predictions or to make suitable changes. It deals in obje ctive, logic, and munotes.in
Page 2
Quantitative Social
Research
2 numbers and puts its focus on convergent reasoning and detailed and
unchanging data.
The data in quantitative research is collected through structured research,
and the results are based on a larger size of samples that represents or
relects the population. An important fact about this kind of research is that
it can be repeated and replicated. The quantitative researcher uses several
tools to gather numerical data that is in the form of statistics and numbers
and is arranged in non -textua l forms like figures, charts, and tables.
Some of the most common quantitative research’s data collection methods
are described here.
Cross -sectional studies
Cross -sectional studies are surveys undertaken at one point in time, rather
like a photo taken by a camera. If the same or similar survey is repeated,
we can get good measures of how society is changing. It is a type of
research design in which data is collected from many different subject at a
given point in time.
Longitudinal studies
Longitudinal st udies follow the same respondents over an extended period
of time. They can employ both qualitative and quantitative research
methods, and they follow the same group of people over time.
Opinion polls
An opinion poll is a form of survey designed to measur e the opinions of a
target population about an issue, such as support for political parties and
views about crime and justice, the economy or the environment.
Questionnaires
Questionnaires collect data in a standardized way, so that useful
summaries can be made about large groups of respondents, such as the
proportion of all young people of a given age who are bullied. Usually
most questions are ‘closed response’, where respondents are given a range
of options to choose from. Researchers have to be careful that the
questions are not ‘leading’, that the options are comprehensive (they cover
every possible answer) and are mutually exclusive, so that only one
answer is correct for any respondent.
Social attitude surveys
Social attitude surveys ask more general questions about beliefs and
behaviour, for example, how often people go to church, how much trust
they have in the police force, whether they think children need a strict
upbringing, how content they are with their life, how often they see other
family mem bers, and whether they are in employment.
munotes.in
Page 3
Quantitative Research – Nature, Characteristics, Significance, Critique
3 Surveys and censuses
A census is a survey of everyone in the population. Because of the vast
number of respondents, they are very expensive to organise. Governments
now depend much more on sample surveys and admin istrative records, for
example those created by a stay in hospital or tax returns. Surveys use a
questionnaire to investigate respondents in a sample. Samples are chosen
in such a way that they can represent a much larger population. A precise
calculation can be made of how accurate the information from any sample
is likely to be.
1.2 NATURE:
Using a deductive approach, quantitative research seeks to establish facts,
make predictions, and test hypotheses that have already been stated. A
large part of the da ta analysis of quantitative research is statistical, striving
to show that the world can be looked at in terms of one reality; this reality,
when isolated in context, can be measured and understood, a perspective
known as positivism (Gay & Airasian, 1999).
There are some features of quantitative research that are inherently
necessary for this approach. A quantitative researcher must: state both the
hypothesis studied and the research procedures that will be implemented
prior to conducting the study, maintai n control over contextual factors that
might interfere with the data collected, use large enough samples of
participants to provide statistically meaningful data, and employ data
analyses that rely on statistical procedures.
Quantitative Research is a sys tematic investigation of phenomena by
gathering quantifiable data and performing statistical, mathematical, or
computational techniques. It collects information from existing and
potential respondents using sampling methods, and surveys, or
questionnaires; the results of which can be depicted in the form of
numerical values (Bhat, 2020). Its purpose is to generate conclusion or to
make some inferential conclusion by trying to quantify the problem and
understand how prevalent it is by looking for projectable results to a larger
population.
Quantitative research is widely used in psychology, economics,
demography, marketing, political science, and educational studies.
Depending on the nature of the study, a researcher can use any of the
following four main typ es of quantitative research, namely: Descriptive
Research, Correlational Research, Causal -Comparative Research or Quasi -
Experimental Research, and Experimental Research.
Check your progress:
1. Elaborate on the nature of quantitative social research.
munotes.in
Page 4
Quantitative Social
Research
4 1.3 CH ARACTERISTICS:
The goal in conducting a quantitative research is to determine the
relationship of one thing to another within a population. It is descriptive,
correlational, quasi -experimental or experimental in nature. Descriptive
and correlation research es establish associations between things under
study while quasi -experimental and experimental studies establish
causality.
As researchers, we should know the characteristics of a quantitative
research listed below (Spalding University, 2020):
1. The data is usually gathered using structured research
instruments.
Before conducting a data gathering, it is a must for a researcher to have his
or her research instrument validated by experts. This validation process for
the structured research instruments is necess ary to ensure the reliability
and validity of the results.
2. The results are based on larger sample sizes that are representative
of the population.
It is necessary for a researcher to correctly determine the number of
respondents in the research to be co nducted in order to absolutely
represent the population.
3. The research study can usually be replicated or repeated, given its
high reliability.
Between qualitative and quantitative research, the latter is easier to
replicate than the former. Since, quant itative research uses a structured
research instrument, and deals with numbers and systematic procedure; it
is highly replicative in nature. The procedure used in a quantitative
research can be repeatedly done to measure the validity of previous
results.
4. Researcher has a clearly defined research question to which
objective answers are sought.
This research questions serve as the backbone of the research. These are
the bases of the structured research questions developed and validated.
5. Data are in the form of numbers and statistics, often arranged in
tables, charts, figures, or other non -textual forms.
Unlike in qualitative research where data and responses are in text form,
or non -numerical data, in quantitative research data are definitely numbers
which are subject to statistical treatment to interpret and generate
conclusion.
6. Project can be used to generalize concepts more widely, predict
future results, or investigate causal relationships. munotes.in
Page 5
Quantitative Research – Nature, Characteristics, Significance, Critique
5 As mentioned, since the results of a quantitative research are based on
larger sample sizes hence it can be used to make inference to a population.
7. Researcher uses tools, such as questionnaires or computer software,
to collect numerical data.
Examples of these are questionnaires, survey forms, and alike which are
validated prior the conduct of the study.
Now, when reporting the results of a quantitative research conducted, it is
necessary to a researcher to remember some tips. A researcher should
explain the data collected how they are collected and how they ar e treated.
It is also advisable to include all relevant results to the research questions
under study. It is a must also to report all the procedure used in data
collection to establish among readers the validity and reliability of results.
The trustworthi ness of the data is the goal. Statistical treatment must also
be appropriate and be explained carefully. When using table or any non -
textual presentation, make sure to present it with clarity.
Check your progress:
1. What are the characteristic features of quantitative social research?
1.4 SIGNIFICANCE:
The importance of quantitative research is that it offers tremendous help in
studying samples and populations. It discusses in detail relevant questions,
for instance, where didthe data come from, where are the existing gaps in
the data, how robust is it and whatwere the exclusions within the data
research. It is vital to note the process for their selection and describe the
methods and tools that are being used by the researcher to collect the
information.
There are four main types of research questions that quantitative research
is particularly suited to finding an answer to:
1. The first type of research question is that demanding a quantitative
answer. Examples are: ‘How many students choose to study educa tion?’
or ‘How many math teachers do we need and how many have we got in
our school district?’ That we need to use quantitative research to answer
this kind of question is obvious. Qualitative, non -numerical methods will
obviously not provide us with the ( numerical) answer we want.
2. Numerical change can likewise accurately be studied only by using
quantitative methods. Are the numbers of students in our university rising
or falling? Is achievement going up or down? We’ll need to do a
quantitative study to find out.
3. As well as wanting to find out about the state of something or other, we
often want to explain phenomena. What factors predict the recruitment of
maths teachers? What factors are related to changes in student
achievement over time? munotes.in
Page 6
Quantitative Social
Research
6 4. The fin al activity for which quantitative research is especially suited is
the testing of hypotheses. We might want to explain something – for
example, whether there is a relationship between the level of poverty and
access to health and medicine.
It discusses in detail relevant questions, for instance, where did the data
come from, where are the existing gaps in the data, how robust is it and
what were the exclusions within the data research. It is vital to note the
process for their selection and describe the me thods and tools that are
being used by the researcher to collect the information.
The quantitative research identities variables that are being measured,
gives a detailed description of the applicable method that is used in
obtaining relevant data, notes d own important criteria about the fact that
the data was already in existence or the researcher gathered himself. Since
its mainly about the statistics, qualitative research is highly resourceful in
gathering numerical data about any phenomena even in socia l science.
Check your progress:
1. Is quantitative social research significant? Why?
1.5 CRITIQUE:
According to Saunders et al. (2009), research methodology serves as the
backbone of a research study. Quantitative research’s main purpose is the
quantificat ion of the data. It allows generalisations of the results by
measuring the views and responses of the sample population. Every
research methodology consists two broad phases namely planning and
execution (Younus 2014). Therefore, it is evident that within these two
phases, there likely to have limitations which are beyond our control
(Simon 2011).
Following are major criticisms/limitations of quantitative social research:
1. Improper representation of the target population
Improper representation of the ta rget population might hinder the
researcher for achieving its desired aims and objectives. Despite of
applying appropriate sampling plan representation of the subjects is
dependent on the probability distribution of observed data. This may lead
to miscalcu lation of probability distribution and lead to falsity in
proposition.
2. Lack of resources for data collection
Quantitative research methodology usually requires a large sample size.
However due to the lack of resources this large -scale research becomes
impossible. In many developing countries, interested parties (e.g.,
government or non -government organisations, public service providers,
educational institutions, etc.) may lack knowledge and especially the
resources needed to conduct a thorough quantitati ve research. munotes.in
Page 7
Quantitative Research – Nature, Characteristics, Significance, Critique
7 3. Inability to control the environment
Sometimes researchers face problems to control the environment where
the respondents provide answers to the questions in the survey (Baxter
2008). Responses often depend on particular time which again is
dependent on the conditions occurring during that particular time frame.
4. Limited outcomes
Quantitative research method involves structured questionnaire with close
ended questions. It leads to limited outcomes outlined in the research
proposal. So, the results cannot always represent the actual occurring, in a
generalised form. Also, the respondents have limited options of responses,
based on the selection made by the researcher.
5. Expensive and time consuming
Quantitative research is difficult, expens ive and requires a lot of time to be
perform the analysis. This type of research is planned carefully in order to
ensure complete randomization and correct designation of control
groups (Morgan 1980). A large proportion of respondents is appropriate
for th e representation of the target population. So, as to achieve in -depth
responses on an issue, data collection in quantitative research
methodology is often too expensive as against qualitative approach.
6. Difficulty in data analysis
Quantitative study requ ires extensive statistical analysis, which can be
difficult to perform for researchers from non - statistical backgrounds.
Statistical analysis is based on scientific discipline and hence difficult for
non-mathematicians to perform.Quantitative research is a lot more
complex for social sciences, education, anthropology and psychology.
Effective response should depend on the research problem rather than just
a simple yes or no response.
Check your progress:
1. What are the major criticism of quantitative rese arch?
1.6 SUMMARY:
Quantitative research is defined as a systematic investigation of
phenomena by gathering quantifiable data and performing statistical,
mathematical, or computational techniques. Quantitative research collects
information from existing an d potential customers using sampling
methods and sending out online surveys, online polls, questionnaires, etc.,
the results of which can be depicted in the form of numerical. After careful
understanding of these numbers to predict the future of a product or
service and make changes accordingly.
Quantitative outcome research is mostly conducted in the social sciences
using the statistical methods used above to collect quantitative data from
the research study. In this research method, researchers and statis ticians munotes.in
Page 8
Quantitative Social
Research
8 deploy mathematical frameworks and theories that pertain to the quantity
under question.
Quantitative research templates are objective, elaborate, and many times,
even investigational. The results achieved from this research method are
logical, sta tistical, and unbiased. Data collection happened using a
structured method and conducted on larger samples that represent the
entire population.
Quantitative research is often placed in opposition to qualitative
research.In many cases, this turns into a ‘p aradigm war’, which is seen to
result fromapparently incompatible world views underlying the methods.
When youlook closer at researchers’ actual beliefs, it appears that the so -
called subjectivist(qualitative) versus realist (quantitative) divide is not
that clear -cut.
1.7 QUESTIONS:
What is quantitative research in social sciences?
List the important characteristics of quantitative research.
Which methods are used for data collection in quantitative research?
1.8 REFERENCES AND FURTHER READINGS
Singh, K. (2007). Quantitative social research methods . SAGE
Publications India Pvt Ltd https://dx.doi.org/10.4135/9789351507741.
Black, T. R. 1999. Introduction to Research Design. In: Black, T. R.
(eds). Doing Quantitative Research in the Social Sc iences . London:
Sage.
Burns, R. 2000. Introduction to Research Methods. London: Sage.
Hughes, C. 2006. Qualitative and Quantitative Approaches to Social
Research . UK: University of Warwick.
Punch, K. 1998. Introduction to Social Research: Quantitative and
Qualitative Approaches. London: Sage.
Tashakkori, A. and Teddlie, C. 2010. Integrating Qualitative and
Quantitative Approaches to Research. In: Bickman, L. and Rog, D. J.
(2nd ed). The Sage handbook of Applied Social Research Methods .
UK: Sage.
Tashakkori, A. and Teddlie, C. 2010. Integrating Qualitative and
Quantitative Approaches to Research. In: Bickman, L. and Rog, D. J.
(2nd ed). The Sage handbook of Applied Social Research Methods .
UK: Sage.
munotes.in
Page 9
9 2
TYPES OF DATA - PRIMARY AND
SECONDARY, SMALL AND BIG
Unit Structure
2.0 Objectives
2.1 Introduction
2.2 Meaning of Data
2.3 Importance of Data
2.4 Meaning of Primary Data
2.5 Meaning of Secondary Data
2.6 Differences between Primary and Secondary Data
2.7 Big Data
2.8 Small Data
2.9 Differences between Big and Small Data
2.10 Summary
2.11 Questions
2.12 References
2.0 OBJECTIVES
To learn about the sources of Data collection – Primary and
Secondary
To learn about Small and Big Data.
2.1 INTRODUCTION
In this chapter, you will learn about Pr imary and Secondary, Small and
Big. The concepts described in this chapter are some of the core concepts
which are used in research methodology. In other words, they are the
foundation for conducting research specially the concepts of Primary and
Secondary data. Till the time you are doing research you will encounter
these words again. Let it be your Master’s program or Ph.D. program.
Before understanding the types of Data let us first look into the meaning
of Data.
2.2 MEANING OF DATA
According to the Cam bridge dictionary the meaning of Data is
Information gathered which can be facts or that of number. This
information is further studied, analyzed, and utilised to aid in the decision -munotes.in
Page 10
Quantitative Social
Research
10 making. Information can also be in digital form that can be saved and
accessed by using a computeri.
2.3 IMPORTANCE OF DATA
Today’s several companies work only on just individuals’ data and thrive
with their businesses on it. There are larger multinational companies too
like Mc Kinsey which works on data of consumer market. If a company
has to sell a product it needs data – as to what is the current demand,
trends, age group, emotion factor through which a product could be sold
etc. In the same way, in social science too, data is also important for
understanding individuals, gro ups, societies. This is needed for several
reasons like for implementing policies, to take enough measures. For
example – During the Covid pandemic it was through data that states
could figure out which areas had more covid cases and declare them as red
zones and prevent outsiders from entering those areas or creating
compulsory social distancing. The Sources of Data Collection has two
parts namely Primary Data and Secondary Data. Let us learn about
Primary Data first.
2.4 MEANING OF PRIMARY DATA -
Primary data is information that is created for the first time by the
researcher via his or her own efforts and expertise, especially to
understand the research problem in better way. Primary data is also known
as raw data or first -hand data. Because primary data collecting is done by
the organization or by individual himself or herself. At times this kind of
data collection is carried out under certain supervision too. Especially
when there is large scale data which is needed to be collected there is a
team invo lved than just one individual. Often primary data is generated
through interviews, Questionaires. However, there are other important
documents too which are viewed as Primary Data for example - letters,
emails, diaries, photographs, and daily schedules. Pe rsonal records include
things like driver's licences and student ID cards. People may preserve a
personal notes of events they have witnessed or participated in, which is
another form of primary data. Birth and death certificates, marriage
licences, and ot her important legal records are stored for a long period in
public institutions and used for genealogical research (family history
research) and other research projects. A property title, a birth or marriage
certificate, a social security card, a diploma, or any document having a
very long -term and significant valueii is also primary dataiii.
Interview and Primary Data
Primary Source of data collection goes hand in hand with the interviews.
An interview can be used as a tool to gather fresh, genuine, and sens itive
information or insights. Interviews, for instance, are a suitable strategy
when discussing themes like violence, conflict zones like communal
violence areas, etc. However, sufficient rapport -building must be done
prior to the interview. Interview als o helps in reducing the gaps between
the participants and the researcher. munotes.in
Page 11
Types of Data - Primary and
Secondary, Small and Big
11 Ethnography and Primary Data
In Qualitative studies Primary Data is used more often. There are research
methods like Ethnography which is often used in the discipline of
Anthropolog y and at times even in Sociology which uses Primary Data to
a large extent. Here the researcher visits a village which could be even
remote away from modern society, facility and then spends several months
and years observing, recording, participating the events of the society and
thereafter he/she documents it. In Ethnography kind of primary data
collection, the researcher at times even learns the language of the people.
This he/she does so that they could think in the local language. The
Ethnographer whil e doing data collection using primary method observe
every minute details, every day life and makes notes about it. There are
several scholars who have used investigates societies themselves like
Malinowski – His famous Works are Magic and Religion, Coming of Age
in Samoa, Indian writers like M.N. Srinivas – His Study of Religion
among Coorg’s, The Remembered Village. Clifford Geertz while studying
the Cockfight in Bali, Indonesia.
Journalistic writings like Everyone Loves a Good Drought – by P. Sainath
is a example of primary data collection – In this book, Sainath travels to
different villages of India and he writes about the lives of the people who
are effected by droughts. Every chapter is a story which is of farmer
difficulties, farmer’s widows, villag e life. The uniqueness about the book
is that it is written in simple language and it connects with the reader. To
understand primary data collection P Sainath work is a recommended
reading. Feminist view primary data as an important source for
documenting the marginalized groups experiences specially females.
Colonisers and Primary Data
The Colonisers sponsored several scholars, researchers, Sociologists,
Linguistics to write about the colonized locations. This in turn helped
them to understand the socie ties better in which they ruled. Several Indian
texts in local languages as a result was translated to English. There was
emphasis laid on the documentation of practices, rituals, food, tribal
cultures etc. There still exists a debate on the kind of conten t – quality or
the reality of the content been produced. At times, several writings can be
viewed as a researcher documenting a text from that of a hierarchical view
point.
2.5 MEANING OF SECONDARY DATA
The data that has been compiled and gathered from ex isting sources is
known as secondary data. The secondary sources are frequently the easily
accessible information that researchers utilise to produce statistical claims
and reports for their investigations. Unpublished materials like PhD
Theses and records can also be considered secondary data. The secondary
data are beneficial since they are already available online and in libraries.
In terms of time and location, secondary sources are likewise unrestricted. munotes.in
Page 12
Quantitative Social
Research
12 It is not necessary for the researcher to be pre sent when and where the
participants are assembled. Consequently, it is also economical.
Examples of secondary data include Census Reports, Annual Reports,
Company Financial Statements, Statistic Statements, Department of
Government Reports, etciv.
Primary data and secondary data are typically contrasted. In contrast to the
former, which is information gathered from sources other than the user,
the latter is derived directly from first -hand sources through
questionnaires, observations, focus groups, or in -depth interviews. Or to
put it another way, secondary data is data that has already been obtained
for a different purpose. Such material, nevertheless, might be quite helpful
for one's research.
A variety of secondary data classifications, including those th at try to
distinguish between raw and compiled data, are used in literature research.
If any processing of the earlier kind has occurred, it has been limited (raw
data). In the case of the latter category, there has been some sort of
selection or summariza tion (compiled data).
Importance of Secondary Data
Secondary Data is useful for a number of ways, right from saving time and
resources to accessibility. Let us look into some of other ways in which it
is helpful.
Developing Argument
Secondary Data is of ten used/can be used to support the primary data. For
example – Imagine you are studying about junk food eating habits among
teenagers. In your study you found out that out of 100 sample – nearly 85
percent of the samples like maggi. The same study conduct ed in some
other city by some other scholar also had the same conclusion. So, here
you can build up an argument that – The findings of my study and X
author study has the same kind of findings. Hence, through this we could
generalize the finding and locate the eating habits of teenagers and take
enough measures, awareness to reprogram the food habits.
Review of Literature
Secondary Data is widely used to build the Review of literature in the
thesis, research papers, reports, any kind of evidence. Let us ta ke the
example of a court case Applications in Mobile and Data leakage. You
must have seen in movies how in the court lawyer to justify their case,
point out the earlier verdict given on a similar issue. For example – The
problem (case) would be would disc uss in Chennai High Court but the
lawyer could be using a point from that of verdict of Kerala High Court.
Secondary data thus, presents a narrative about the body of work carried
out earlier in the given field, area this is then presented through
compilat ion as Review of literature. Through secondary data it is also
shown how the existing gaps in the research topic exists. Hence, even munotes.in
Page 13
Types of Data - Primary and
Secondary, Small and Big
13 when a researcher/ student is first starting with his study – the first advice
is given by the teacher/supervisor is to rea d on the topic – i.e., collect all
the secondary sources.The following are list of resources from where
Secondary Data could be collected -
The OECD's (Organisation for Economic Co -operation and
Development).
UNICEF has contributed to the change of the d ata environment for
more than 20 years by making strategic investments in data collection. The
Multiple Indicator Cluster Surveys (MICS) programme is the central
component of this methodology. UNICEF supports governments in
conducting household surveys in nations as diverse as Argentina, Bhutan,
the Democratic Republic of the Congo, and Iraq through a global
programme of methodological research and technical assistance. The
results of MICS have been widely used as a basis for policy decisions,
programme eff orts, and voter persuasion on issues involving children and
women around the world. All of the available MICS datasets and
conclusions are available at mics.unicef.org.
NSSO Data - The National Sample Survey is a important component
in in India which is us ed for policy building. It has data on Employment
and unemployment, housing conditions, domestic tourism, drinking water,
sanitation, land and animal holdings, social consumption, health, domestic
tourism expenditure, Labour Force, Construction, Industries , Manufacture,
and so on are all covered by the NSSO round.
• Annual Industry Surveys - The Annual Survey of Industries includes the
production facilities in the registered sector. It includes comprehensive
data on the inputs, outputs, value added, personn el, assets, and other
factors of the registered factories.
Consumer Expenditure in the Home - These surveys track how
much money and how many different things households spend each year
on. Surveys are carried outboth annually and five years.
Business Sur veys - These studies provide data on input, output,
value added, employment, and other variables in unorganised industries
like trade, production, and services.
Surveys of Land and Livestock Holdings are conducted
approximately every ten years and provide information on active land and
livestock holdings in rural areasv.
2.6 DIFFERENCES BETWEEN PRIMARY AND
SECONDARY DATA
The following details emphasise the fundamental distinctions between
primary and secondary data: munotes.in
Page 14
Quantitative Social
Research
14 1. "Primary data" refers to information that the researcher has collected for
the first time. Secondary data refers to information that has already
been gathered others, organisations.
2. Primary data are up -to-date information, whereas secondary data are
older information.
3. Primary data is gathered to address the issue at hand, as opposed to
secondary data, which is gathered for a number of reasons than just to
address a present situation.
4. It takes a long time to gather primary data. The acquisition of secondary
data, however, is rapid an d simple.
5. Surveys, observations, experiments, questionnaires, and in -person
interviews are a few types of primary data collection techniques.
Official documents, websites, books, journal articles, internal records,
and other materials are examples of se condary data gathering sources.
6. A lot of time, money, and labour must be put into gathering primary
data. Secondary data, on the other hand, is freely available and fairly
priced.
7. The primary data is constantly modified to meet the needs of the
resea rcher, and the lead researcher is in responsibility of ensuring that
the research is of a high standard. However, the quality of secondary
data is outside the researcher's control, and it is not adapted to his
requirements.
8. Primary data is available in its unprocessed form, whereas secondary
data is a polished version of primary data. Secondary data is created
when statistical tools are applied.
Check Your Progress
1. Primary data is collected by whom?
2. Do you think primary data and Secondary data are same?
2.7 BIG DATA
Big data is a collection of structured, semistructured, and unstructured data
that is gathered by businesses and may be mined for information for use in
advanced analytics applications like machine learning and predictive
modellingvi.
Big Data is large scale data which is stored across several parallel
computers. Today more people are using technology, and there are now
more connected devices than ever. Companies that connect the physical
world to digital media are always thinking of new ways to draw in
customers. This shows how much more data and information will be
circulating in the digital world now and in the years to come. Future
businesses will have to process, look at, and use a lot more data. munotes.in
Page 15
Types of Data - Primary and
Secondary, Small and Big
15 Use of Big Data
Big Data is used in a variety of fields and industries, including geoscience,
social media, banking, e -commerce, healthcare, environmental and climate
studies, life sciences and drug development, e -library and academic
publications, cybersecurity, and governancevii.
Big Data i s helpful when business owners must make important decisions
for growth. They hire specialists to extract pertinent data from Big Data
Analytics, which could benefit the organisation. To make important
decisions and advance, businesses may considerably ben efit from the
insights provided by a big data professional.
The three V's of big data are variety, velocity, and volume.
Data Volume: There is a vast amount of data.
Versatility: Consists of a wide range of data types.
Velocity: Near -real-time evaluation o f a vast amount of streaming data.
2.8 SMALL DATA
Small data is a term used to describe a collection of small datasets that can
influence current behaviour. anything that can be gathered into an Excel
spreadsheet. Small data is only meant to have a small impact over a short
time, yet it can still be useful in decision -making.Small Data is the term
used to describe the specialised datasets produced after sorting through
vast amounts of data. There are a number of issues in a corporation that
demand rapid at tention. Big Data analysis methods don't need to be used
in circumstances like these.
Small volumes of data are gathered to be analysed. It's a sample size that
the data scientist selected to address the particular question at hand. Small
data allows for c ontrol over the data. The prepared data has been ready for
study for some time now.It has distinct dataset qualities that are easy to
understand and may be used to analyse current events.
2.9 DIFFERENCES BETWEEN BIG AND SMALL DATA
OBJECTIVE: A single tas k can be finished by looking at modest
amounts of data. On the other hand, the goal of big data increases and
directs to unexpected scenarios. We may start out with a single goal, but it
will change with time.The cloud's numerous servers are used for shar ing a
Big data. On the otherhand, small data is type of data which is stored in a
single computer. The size of Big Data is measured in terabytes and
tetabytes. While that of the small data is that of measured in terms of mg
or gb.
LOCATION: Small data is typically kept on a local computer or in a
database as a single file. On the other hand, big data is scattered among
numerous servers located in diverse locations using the cloud. munotes.in
Page 16
Quantitative Social
Research
16 STRUCTURE: Big data may be semi -structured or unstructured across
multiple s ources, in contrast to organised small data, which is provided in
a single table.
End users frequently prepare little amounts of data for their own unique
purposes. Because of this, the person entering the data is aware of how to
use it and what to anticip ate from it. On the other hand, a group of people
who may or may not be end users create big data. The collaboration
required to manage the data is therefore somewhat complex.
LONGEVITY: Short -term data can be kept for a limited time or until the
task is f inished. On the other hand, big data requires permanent storage.
REPRODUCIBILITY: If a tiny amount of data is mistakenly lost or
corrupted, it is feasible to recreate it; nevertheless, enormous amounts of
data cannot be replicated. Therefore, it should be carefully inspected and
evaluated before any dangerous material is removed.
RISK: In tiny data, the risks are very low. On the other hand, big data is
risky because it requires a lot of resources including cash, labour,
materials, and time.
INTROSPECTION - When dealing with modest amounts of data, we are
given well -organized, discrete data pieces that are simple to find and have
explicit metadata that explains all of the columns. Finding many files in
various formats, meanwhile, could be challenging in case s with huge data.
Insufficiently recorded data can be difficult to understand.
ANALYSIS: Several sorts of analysis can be performed using a variety of
data.
On a single system, small amounts of data can be analysed in a single
process. Huge data may need t o be divided up and examined in stages
using various approaches in dispersed scenarios.viii
Check Your Progress
1. List out few uses of Big Data
2. Discuss two comparison with reference to small and big data
2.10 SUMMARY
Primary data is information that is created for the first time by the
researcher via his or her own efforts and expertise, especially to
understand the research problem in better way. Primary data is also known
as raw data or first -hand data. Because primary data collecting is done by
the or ganization or by individual himself or herself. On the other hand
secondary data is the data that has been compiled and gathered from
existing sources. The secondary sources are frequently the easily
accessible information that researchers utilise to produ ce statistical claims
and reports for their investigations. Unpublished materials like PhD
Theses and records can also be considered secondary data. The secondary munotes.in
Page 17
Types of Data - Primary and
Secondary, Small and Big
17 data are beneficial since they are already available online and in libraries.
In terms of tim e and location, secondary sources are likewise unrestricted.
It is not necessary for the researcher to be present when and where the
participants are assembled. Consequently, it is also economical.Examples
of secondary data include Census Reports, Annual R eports, Company
Financial Statements, Statistic Statements, Department of Government
Reports, etc. Small data is a term used to describe a collection of small
datasets that can influence current behaviour. anything that can be
gathered into an Excel spread sheetThe size of Big Data is measured in
terabytes and tetabytes. While that of the small data is that of measured in
terms of mg or gb.Big Data is large scale data which is stored across
several parallel computers. Today more people are using technology, and
there are now more connected devices than ever.
2.11 QUESTIONS
1. Distinguish between big and Small Data
2. Write a brief note of Secondary Data and discuss some examples
3. Discuss Primary Data and some methods of collecting them.
2.12 REFERENCES
ihttps://dictionary.cambridge.org/dictionary/english/data
iihttps://researchguides.ben.edu/c.php?g=282050&p=7037030
iiiKothari, C. R. (2004). Research methodology: Methods and techniques .
New Age International.
ivKrishnaswamy O.R. (2010), Methodology of Research in Social Science,
Himalaya Publishing House.
vhttp://microdata.gov.in/nada43/index.php/catalog/central
vihttps://www.techtarget.com/searchdatamanagement/definition/big -data
viihttps://www.sciencedirect.com/journal/big -data-research/a bout/aims -
and-scope
viiihttps://medium.com/analytics -vidhya/small -data-vs-big-data-
30a38f129074
munotes.in
Page 18
18 3
THEORETICAL CONSIDERATIONS –
POSITIVISM
Unit structure :
3.0 Objectives
3.1 Introduction
3.2 ‘Positivism’ – The Background
3.3 The French Tradition of Positivism
3.4 Central Tenets of Positivism
3.5 Summary - ‘Positivism’ And Sociology
3.6 Questions
3.7 References and Further Readings
3.0. OBJECTIVES:
To familiarize students with Positivist theoretical paradigms
To understand that ‘positivism’ is a philosophical paradigm, based
upon natural science of reason and logic.
3.1 INTRODUCTION:
Positivism is a ph ilosophy of science that rejects metaphysical speculation
in favor of systematic observation using the human senses. “Positive”
knowledge of the world is based on generalizations from such
observations that, given sufficient number and consistency, are reg arded
as producing laws of how phenomena coexist or occur in sequences
(Lewis -Beck et al., 2004).
The doctrine of positivism was formulated by Auguste Comte, the French
philosopher, who is also known for being one of the founding fathers of
sociology. Pos itivism is regarded as the scientific understanding of
society. Although positivism, as a research paradigm, concerns itself with
the social sciences, it draws heavily from the natural science. Positivism,
being based on the principles of natural science, argued for the study of
the society driven by scientific investigation and knowledge.
However, as noted by Bryant (1985), the terms 'positivism' and 'sociology'
are both commonly supposed to have originated with Comte, and in
particular his Cours de philo sophie positive (6 vols, 1830 -42), although
true of the second, this is misleading with respect to the first term insofar
as Comte wrote not about 'positivism' but about 'the positive philosophy' munotes.in
Page 19
Theoretical considerations –
Positivism
19 and 'the positive method', and Saint -Simon before him had al so advocated
a positive philosophy.
3.2 ‘POSITIVISM’ – THE BACKGROUND:
The philosophy of positivism was to solve the problems of social life, its
progress by following the principles of natural science. In A General View
of Positivism French philosopher Au guste Comte (1798 -1857) gives an
overview of his social philosophy known as Positivism (Comte, [2009]
1848 ). The French Revolution had deep impact on the thinking of Aug uste
Comte, to the extent that he rejected religion professed ‘religion of
humanity’. Comte strongly felt that the scientific study of society would
be the only way to solve its problems and thus named it ‘sociology’.
Based on scientific principles, Comte formulated the doctrine or
philosophy of ‘positivism’, mainly through his six -volume work Course of
Positive Philosophy , over a decade. Following the natural science
principles, Comte proposed to look at the society as being governed by its
own set of law s, just as the physical sciences. He, thus laid down the
foundation of the scientific study of society, to become popular as
‘sociology’. The uncertainty and chaos in the social life was to be resolved
by the use and application of these scientific princip les. Positivism in
philosophy came to be associated with epistemologies which make
experience the foundation of all knowledge. and also with their
complementary ontologies which propose a division between objects
which are accessible to observation and obj ects which are not Bryant
(1985 ).
Comte was also significantly influenced by the early intellectuals. From
David Hume and Immanuel Kant Comte derived his conception of
positivism —i.e., the theory that theology and metaphysics are earl ier
imperfect modes of knowledge and that positive knowledge is based on
natural phenomena and their properties and relations as verified by the
empirical sciences ("The New Encyclopaedia Britannica," 1997 ). From the
beginning, Positivism believed in the reality being accessible through our
senses. Human experience plays an important role in acquiring the
knowledge of reality. Thus, the validity through experience remains
crucial for positivist approach. In positivism, the scientific knowledge has
to be verifiable through human experience.
Comte’s main contribution to positi vist philosophy falls into five parts: (a)
rigorous adoption of the scientific method; (b) law of the three states or
stages of intellectual development; (c) classification of the sciences; (d)
conception of the incomplete philosophy of each of these scien ces anterior
to sociology; and (e) synthesis of a positivist social philosophy in a unified
form (Duignan, 2010 ). Comte’s law of three stages – a theological stage,
metaphysical stage and positive stage – outlined the process of hu man
intellectual development in the history of society.
Check your progress:
1. What is Positivi sm? munotes.in
Page 20
Quantitative Social
Research
20 3.3 THE FRENCH TRADITION OF POSITIVISM:
It is well known that Comte not only coined the term ‘sociology’ but also
introduced and systematized the positivis t philosophy in the social science.
Saint -Simon, in fact, provides a better starting point for an analysis of the
French tradition of positivism than Comte for two reasons:
(a) he announced the great nineteenth century project of the construction
of a pos itive science at the start of the century,
(b) he did so in a way that attracted admiration from Marx and Durkheim
(Bryant, 1985).
The works of Saint -Simon, Comte and Durkheim display interconnections
in their thinking and ideas. Bryant (1985) lists twel ve tenets, which
indicate the basic characteristics of the French tradition of positivism:
i. There is but one world, and it has an objective existence.
ii. The constituents of the world, and the laws which govern their
movements, are discoverable through science alone, science being the
only form of knowledge. Therefore that which cannot be known
scientifically, cannot be known.
iii. Science depends upon the combination of reason and observation.
iv. Science cannot discover all the constituents of the worl d, and all the
laws which govern them, because human powers of reason and
observation are limited. Scientific knowledge will remain forever relative
to the level of intellectual development attained and to progress in the
social organization of science.
v. What man seeks to discover about the world is normally suggested by
his practical interests and his situation.
vi. There are laws of historical development whose discovery will enable
the past to be explained, the present understood and the future predict ed.
vii. There are social laws which govern the interconnections between
different institutional and cultural forms.
viii. Society is a reality sui generis.
ix. Social order is the natural condition of society.
x. Moral and political choice should be estab lished exclusively on a
scientific basis.
xi. The subjection of man before the natural laws of history and society
precludes evaluation of institutional and cultural forms in any terms other
than those of conformity with these laws. munotes.in
Page 21
Theoretical considerations –
Positivism
21 xii. The positive, the constructive, supersedes the negative, the critical.
The positive, the relative, also supersedes the theological and the
metaphysical, the absolute.
Check your progress:
1. What are the characteristics of the French tradition of positivism?
3.4 CENTRAL TEN ETS OF POSITIVISM:
Blaikie (2007 ), through his meta -analysis of the literature on ‘positivism’,
has presented some brief points to be incorporated as positivism’s
characteristics or its central tenets. There are:
Phenomenalism: this rule asserts the acquisition of scientific
knowledge only through human experience. Scientific knowledge is
nothing but the percepti on by the senses, a ‘pure experience’, without any
cognitive interference.
Nominalism: Any abstract concepts used in scientific explanation
must also be derived fromexperience ; metaphysical notions about which it
is not possible to make any observations have no legitimate existence
except as names or words. Hence, the language used to describe
observations must be uncontaminated by any theoretical notions. As
‘reality’ or ‘truth’ is believed to be observable through one’s senses, any
theoretical terms, su ch as ‘God’, which is non -observable, should be
considered as meaningless.
Atomism: The objects of experience, of observation, are regarded as
discrete, independentatomic impressions of events, which constitute the
ultimate and fundamental elements of the world. In so far as these atomic
impressions are formed into generalizations, they do not refer to abstract
objects in the world, only regularities among discrete events.
General Laws: Scientific theories are regarded as a set of highly
general law -like statements ;establishing such general laws is the aim of
science. These laws summarize observations by specifying simple
relations or constant conjunctions between phenomena. Explanation is
achieved by subsuming individual cases under appropriate laws. Thes e
laws are general in scope, in that they cover a broad range of observations,
and are universal in form, in that they apply, without exception, across
time and space.
Value Judgments and Normative Statements: “Facts” and “values”
must be separated asvalu es do not have the status of knowledge. Value
statements have no empirical content that would make them susceptible to
any tests of their validity based on observations.
munotes.in
Page 22
Quantitative Social
Research
22 Verification: The truth or falsity of any scientific statement can be
settled with re ference toan observable state of affairs. Scientific laws are
verified by the accumulation of confirming evidence.
Causation: There is no causality in nature, only regularities or
constant conjunctionsbetween events, such that events of one kind are
follo wed by events of another kind. Therefore, if all we have are
regularities between types of events, then explanation is nothing more than
locating an event within a wider ranging regularity.
Check your progress:
1. What are the central tenets of ‘Positivism ’?
3.5 SUMMARY - ‘POSITIVISM’ AND SOCIOLOGY:
Positivism in sociology has come to be associated with the very idea of a
social science and the quest to make sociology scientific (Bryant, 1985).
Positivists look at social reality as scientifically verifiable and measurable.
Just as the physical world is governed by the laws, human existence is also
governed certain laws that should be discovered, the positivists believe.
And therefore, sociology, from a positivist perspective, is also modelled
on the laws of the natural sciences, which necessarily include logic and
reasoning.
As sociology deals with the scientific study of society, positivism ensures
scientific explanations – which are observed, verified and logically stated
– of social phenomena, as it compl etely rejects theological or supernatural
assumptions and explanations. As social actors remain important in the
social phenomena, however, the positivist philosophy, within sociology,
looks at the factual aspects of the phenomena, devoid of any subjectivi ty
and value judgments of the actors or the researchers.
Romm (1991), through a meta -analysis of existing literature, affirms that
the positivist theory of science is not the only theory which has become
incorporated into the sociological enterprise, but this theory of science,
and the research practice which it inspires, have assumed a dominant
position within sociology. Thus the positivist pursuit of the sociological
understanding of the society entails understanding the causal aspects of
human behaviour s, in order to understand how society operates.
Positivism in sociology shares a strange relationship. Sometimes, to be
positivist means no more than being scientific, although that fails to
discriminate between positivism and all the other sociologies tha t have
claims to be scientific in perhaps different ways, such as Marxism,
functionalism, structuralism, and so on; and sometimes, positivist
sociology is synonymous with statistical analysis, as in many sociological
research reports and methods textbooks; yet some other times, to practice
positivist sociology is to seek to establish causal explanations, or to search
for fundamental laws of human behaviour or historical change, or to insist munotes.in
Page 23
Theoretical considerations –
Positivism
23 upon objective empirical information systematically organized to ge nerate
or test hypotheses (Halfpenny, 2014).
Thus, for a positivist sociological investigation, we need necessarily need:
an empirical basis of knowledge, where direct observation leads to the
theory; the place of deduction and induction in linking 'theor y' and
'observation'; constructing a hypothesis; tentative character of scientific
statements; demarcation between science and non -science; objectivity; and
establishing the causality.
3.6 QUESTIONS:
Elaborate on the positivist research methodology within Sociology.
Elaborate on ‘Positivism’ as a classical methodological perspective.
Elaborate on the French Tradition of Positivism.
What has been Comte’s contribution to the philosophy of positivism?
How is ‘positivism’ incorporated into Sociology?
3.7 REFERE NCES AND FURTHER READINGS
Anand, S. (1997). Understanding Religion: Theories and
Methodology . New Delhi: Vision and Venture.
Blaikie, N. (2007). Approaches to Social Enquiry . United Kingdom:
Polity Press.
Brennan, J. F., & Houde, K. A. (2017). Sensationalism and Positivism:
The French Tradition History and Systems of Psychology (7 ed., pp.
123-136). Cambridge: Cambridge University Press.
Bryant, C. G. A. (1985). Positivism in Social Theory and Research .
London: Macmillan Publishers Limited.
Comte, A. ([2009] 1848). A General View of Positivism (J. H. Bridges,
Trans.). USA: Cambridge University Press.
Halfpenny, P. (2014). Positivism and Sociology: Explaining Social
Life. London: Taylor & Francis.
Mill, J. S. (2009). Auguste Comte and Positivism . New York: Cosimo
Classics.
munotes.in
Page 24
24 4
WRITING RESEARCH PROPOSAL
Unit Structure
4.0 Objectives
4.1 Introduction
4.2 Meaning of Research Proposal
4.3 The process of writing
4.4 A quantitative proposal's format
4.5 Format for a Mixed Methods Proposal
4.6 Qualitative Research proposal
4.7 Summary
4.8 Questions
4.9 References
4.0 OBJECTIVES
1.0 To understand the meaning of Research proposal and its uses.
2.0 To learn proposal writing from certain examples of existing proposals.
4.1 INTRODUCTION
In this chapter we are going to learn about research proposal its meaning,
the objecti ve behind making of writing research proposal, the different
kinds of research proposal used. Research Proposal is, an idea/ problem is
being proposed to a guide/ committee/ Institution and there after it is
accepted or rejected or some modification is sug gested.
4.2 MEANING OF RESEARCH PROPOSAL
A research proposal is a thorough description of a proposed study to look
into a certain issuei.A detailed summary of the dissertation or research
project is also contained in a proposal. It demonstrates the desig n and
methods of the studyii.The goal of a research proposal is to persuade
readers with the idea that the proposal is a wort hwhile study, topic and
researcher has the education and experience required to carry it out. The
research proposal generally has t o answer the questions like following
issues: What the researcher is planning to do, how he/she is planning to
accomplish itiii.
Writing a research proposal is a challenging procedure in today's world
because of the research design trends that are constantly changing and the
requirement to include scientific breakthroughs into the technique. The munotes.in
Page 25
Meaning of Research Proposal
25 most important phase of the research process is the development of a
clear, well -thought -out proposal that will serve as the basis for the
research. Writing a study p roposal is done in order to apply for grants and
obtain approval from a number of bodies, including the ethical committee.
The requirements for producing a high -quality research proposal change
based on the needs of the funding agency or institution becaus e there is no
universal standard way that is followediv.The most important thing though
is that proposal must be able to persuade the review panel evaluating the
study of the validity, viability, practicability, and generalizability of the
study's designv. The process of conducting research includes multiple
stages and a flow of documents. The order and stages of the process that
have a real impact on the quality and content of the final report and the
research materials created at every level. The four docu ments mentioned
in the research proposal are research summary, research abstract, and the
research repor t which are used to evaluate the appropriateness, quality,
and validity of every research/study.
Length of Proposal –
It is preferable to contact the i nstitution/organization where the proposal is
being sent. To save time, this step should be completed before writing the
proposal. The proposal typically has between 10 and 20 pages. References
and a reading list are also included at the end of the researc h proposal.
A research proposal needs to be organised clearly. It must be broken up
into paragraphs with subjects and subtopics. Subject changes may be
noted with headings and paragraphs. The discussion's direction is
indicated by the headings. A research proposal needs to be written in a
distinct manner from other academic writing assignments including
essays, fiction, and poetry. The latter makes use of the word's richness.
However, research reports should be written at a formal level ,
needs standard Eng lish since they are a formal presentation of a
problemvi.
Time required –
Before preparing a proposal, the topic must be defined. Because doing so
would save time and enable a person t he researcher to concentrate on a
single issue. While writing a proposa l, there are several modifications that
happen. especially if a guide is present. There are modif ications made ,
new points are added , and proofread. Therefore, preparation must begin on
day one; a little writing each day would aid in finishing the work.
Important Questions
Some important questions which an individual needs to ask before writing
a proposal to oneself is which according to Maxwell (2005) are –
What do readers need to know in order to grasp the topic better?
What aspects of the subject are readers unfamiliar with?
Prior Things to Think About like What do es one want t hrough the
research? munotes.in
Page 26
Quantitative Social
Research
26 What is the environment , context and who will be the subjects of the
study ?
What is the process of Data collection and analysis ?
What will be the process employed to cross check the data ?
What will be the theory used ?
What moral dilemmas will the study bring up?
What do early findings indicate about the applicability?
It is difficult to understand research proposal without understanding the
why it is used.
1. For admission in Philosophy of Doctorate (Ph.D.)
To enroll for Ph.D. firstly an individual needs to have a Master’s
Degree, then he/she need s to clear any one of the entrance exams
likeNational Eligibility Test, State Eligibility test or PET (PhD
entranc e test). When a student wishes to apply for the program of PhD
after Masters Degree the first thing the individual does is finds out a
research problem/ topic and then build a research proposal based on
that. This proposal the candidate prepares individuall y or with help of
some teacher.
2. Non-Governmental Organizations
Writing proposal or research proposal is not just restricted to higher
education but it is alsouse in the development sector like non -
Government organisations like for seeking funds. The NGO s make
proposals to Government seeking funds for implementing a project,
conducting Survey, Conducting Research. Proposals are also
submitted to Corporates, National and Multinational Companies,
Trusts, International Bodies like WHO, UNESCO, IMF, World Ban k
etc.Based on the funds earned they further take action and work in
villages. However, the focus in this chapter is more towards academic
writing.
Check Your Progress
1. Why is a research proposal made?
2. Discuss the length of research proposal.
4.3 THE PROCESS OF WRITING
Writing itself can be a challenging task for several individuals. The
challenge is more with that of technology and access to it. As writing itself
is a creative task one needs a certain amount of dedication, consistency in
it. There a re invisible problems one could encounter too like handling
criticism of past writing and face one’s own fear. As students often tend to
generally write only majorly during exam for exam papers. In a way, we
tend to write what we have studied or what we ha ve read. However,
research proposal is a step towards independent writing and on a topic
which you choose to work upon. Beginning to write a research proposal
would take some amount of mental preparation. munotes.in
Page 27
Meaning of Research Proposal
27 The individual who is making the research proposal is often expected to
make several drafts and a brief proposal or plan explaining the research
project's purpose and methodology before submitting the dissertation. This
is an efficient method of getting ready for your study and it will motivate
you to con sider many of the topics that are mentioned in the next section.
The proposal will ask you to demonstrate some knowledge of the literature
in your chosen field —for example, by naming several key authors or
significant research studies —in addition to outlin ing your proposed
research design and methods, the topic area in which your study is going
to be located, and the research questions that you intend to address.
Based on this information, a supervisor who is knowledgeable in your
study area of interest or who has experience with your suggested research
approach may be assigned to you. The proposal can serve as a valuable
starting point for discussions with your supervisor about your research
topic, and if it includes a timetable for the project, it can be u sed to
schedule frequent meetings to discuss your progress. By giving you a
series of continuing objectives to work toward and forcing you to think
about various parts of the entire research process, such as the various
stages of your research and their ti ming, creating a timeline may be very
helpful.
You will likely need to address a variety of topics when creating a
research proposal like What is the subject of your research, or, alternately,
what are the goals of your research? • Why is the subject of yo ur study (or
the goals of your study) significant?
What is your research question, or what questions do you have? • What
does the body of research indicate about your study's subject, goals, and
research question(s)? • How will you go about gathering infor mation
pertinent to your research question(s)? In other words, what research
techniques do you plan to employ? • Why are the sources and research
methodologies you've chosen the best fit for your research question(s)? •
What equipment (such as postage, tra vel expenses, or software) will you
need for your research, and how will you pay for it? • What schedule do
you have for the various phases of the project? • What difficulties do you
foresee in conducting the research (for instance, gaining access to
organ isations)? • What potential ethical issues could arise from your
research? • How will you analyse your data?
Writing a proposal is consequently helpful for getting your research
project off the ground and motivating you to establish reasonable goals.
The research proposal could make up a modest portion of the overall
evaluation of the dissertation or report that results from the project in
various higher education institutions. It is vital to keep in mind that,
although though the research proposal is a w orking document and the
concepts you provide in it can be polished and developed as your study
advances, doing so will cost you valuable time that could be used to finish
the dissertation by the deadline. munotes.in
Page 28
Quantitative Social
Research
28 In conclusion, a re search proposal can be crafted t o appeal to the
readership. Popular r esearch proposals should be able to expand readers'
knowledge in some little ways, assist readers in finding the information
they need inside the proposal. In addition, be aware of at least some of the
preferences of th e target audience and accommodate those preferences
through thoughtful research design. A writer needs to be aware of and
steer clear of a few frequent mistakes. As follows:
Avoid o veruse of jargon
-Reduce the Verbosity
- Be aware of the i ndividual bias in writing
- Be conscious of any i naccuracies in the facts
- Revise to reduce the Grammatical mistakes
- Avoid illogical statements
-Try to have a sequence
- Include proper references
While d esigning a Proposal's Sections some research hints discussed in the
below section can be used while creating the overall format of a proposal.
Writing Techniques and Ethical Issues
• Ideas for additional areas often come to mind while working on one
section. Create an outline first, and then quickly jot down somethin g for
each part to get thoughts down on paper. The sections can then be
improved later. However, if you fail to write or build an outline, the
process could become time consuming. Look for ideas from other
proposal and make points and review them carefully . Request copies of
proposals that your advisor / supervisor thought that were particularly
strong and deserving of consideration from committees.Examine the
subjects covered, the sequence in which they are addressed, and the level
of information employed t o create the proposal.
• Check to see whether your programme or school offers a course on
developing proposals or a related subject. Such a class would be beneficial
as a support system for your project and as a source of people who can
respond to your pro posal ideas as they emerge.
• Discuss the preferred proposal format with your adviser over a meal. It's
possible that your adviser or graduate committee won't find the material
they're looking for in the parts included in published journal papersvii
munotes.in
Page 29
Meaning of Research Proposal
29 4.4 A QUANTITATIVE PROPOSAL'S FORMAT –
This format is follow ed in several quantitative studies and the outcome is
reported in journal publications. The structure typically consists of an
introduction, a review of the relevant literature, followed by methods,
results, and discussion. To create a dissertation proposal and prepare a
quantitative study, take into account the stud y’s goals and boundaries
theoretical vantage point , Inquiry -based statements or hypotheses , Writing
Techniques and Ethical Issues . One ne eds to also include a n analysis of
the literature , Methods , Research methodology Participants, sample, and
population Instruments, variables, and materials for data collecting
techniques , data analysis , ethical problems that one might encounter while
condu cting the investigation .
General Format of Research Proposal
The proposal's front page includes information like -
Your Name
Qualification
Topic of Proposal
Seeking for Guidance Under (if known and confirm them)
Name of University
Year Month
The topic of the proposal need to focus on the core problem under study.
The Introduction part of the proposal needs to explain the problem under
study with a broader perspective. The Aims and objectives are also
included. Review of literature includes the secondary da ta available on the
topic like that of thesis, books, journal articles, reports any other reference
material connected to the topic. The next section focusses on the research
methodology which discusses the data, the rationale behind choosing the
specific subjects, the limitations, number of subject. The next section
includes the time, resources. Include budget (if proposal is being
submitted to organizations).
4.5 FORMAT FOR A MIXED METHODS PROPOSAL
When using a mixed methods design, the researcher combi nes methods
from both the quantitative and qualitative forms (see Creswell & Plano
Clark, 2007). One has to look into the d eficits in prior research, as well as
one gather information related to both quantitative and qualitative data .
Information should be also documented about the target audiences needed
in the research, t he project's goal and justifications for using a mixed -
methods study . The proposal should also include t he research propositions
and questions (quantitative questions or hypotheses, qualit ative questions,
mixedmethods questions , Literature on the philosophical underpinnings of
employing mixed methods research should also be included.
An explanation of mixed -methods analysis ,the design style employed and
its concepts, p roblems that may aris e when adopting this approach and
how they can b e used to solve the problem has to explained. References munotes.in
Page 30
Quantitative Social
Research
30 and appendixes with instruments, protocols, visuals needs to be also
included at the end.
4.6 QUALITATIVE RESEARCH PROPOSAL –
The following are the st eps which is used for Qualitative research
proposal.
Introduction
Description of the issue (issue, significance of issue)
The study's goals and boundaries
Theoretical vantage point
Inquiry -based statements or hypotheses
Writing Techniques and Ethical Issu es
An analysis of the literature
Methods
Research methodology
Participants, sample, and population
Instruments, variables, and materials for data collecting
Techniques for data analysis
Ethical problems that the investigation might encounter.
initial rese arch or pilot tests
Appendices: Tools, Schedule, and Budget Proposal
Ethics and Plagiarism
The researcher should take extra effort to make sure that moral obligations
are honoured. The protection of the participants' rights, including their
right to inform ed consent, the institutional review process, their right to
autonomy, their right to privacy, their right to confidentiality, their right to
fair treatment, and their right to be free from discomfort and harm, are all
considered ethical issues (ethical ap proval). The researcher must offer
sufficient details.
Participants, the research site, and the appropriate authorities must all give
their informed consent.
Another important point to remember while building a proposal is also
that one has to cite all the sources from which the idea, material, citation,
paragraph, lines has been taken. If one doesn’t cite the content would be
seen by the reader as yours and that is inappropriate. Hence, it is very
important to acknowledge others work. This works as a cumul ative
scholarship where other person would acknowledge your work tomorrow
when ever your work is published. One has to also cite previously
published work if used in the main text of the proposal. As without that munotes.in
Page 31
Meaning of Research Proposal
31 doing that it could lead to self -plagiarism which is also seen as unethical
way.
Check Your Progress
1. Explain ethics while writing research proposal
2. Discuss plagiarism practice in research proposal
4.7 SUMMARY
We began the chapter by understanding the meaning of research proposal.
A research proposal is a thorough description of a proposed study to look
into a certain issue .A detailed summary of the dissertation or research
project is also contained in a proposal. It demonstrates the design and
methods of the study
The goal of a research propo sal is to persuade readers with the idea that
the proposal is a worthwhile study, topic and researcher has the education
and experience required to carry it out. The research proposal generally
has to answer the questions like following issues: What the re searcher is
planning to do, how he/she is planning to accomplish it . A research
proposal is submitted to Universities, Departments for higher education
generally. It is also used when applying a research project to an
organization. The Research Proposal is also used by Non -Governmental
Organisations.
The topic of the proposal needs to focus on the core problem under study.
The Introduction part of the proposal needs to explain the problem under
study with a broader perspective. The Aims and objectives are also
included. Review of literature includes the secondary data available on the
topic like that of thesis, books, journal articles, reports any other reference
material connected to the topic. The next section focusses on the research
methodology which di scusses the data, the rationale behind choosing the
specific subjects, the limitations, number of subjects. The next section
includes the time, resources. Include budget (if proposal is being
submitted to organizations). Ethics, consent should be discussed in the
proposal too. Citation of the used material has to be made while writing
the proposal. While writing the research proposal the language has to be
formal. There should not be any unnecessary jargons used. The written
text should be based on facts an d presented in a logic and sequential order.
The chapter also discusses the mixed method proposal, quantitative and
qualitative proposal too which is similar in the core points but has little bit
of variation amongst each other.
4.8 QUESTIONS
1. Discuss the meaning of Research Proposal and write about Mixed
Methods Research proposal.
2. Explain the Writing process involved with research proposal
3. Discuss quantitative and qualitative research proposal format.
munotes.in
Page 32
Quantitative Social
Research
32 4.9 REFERENCES
iTraenkel JR, Wallen NE. How to design and evaluate research in
education. On line learning center with power web. Available
at www.highered.mcg raw-
hill.com/sites/0072981369/student_view0/chapter24/key_terms.html
iiWalliman, N. (2006). Writing a research proposal. In Social research
methods (pp. 186 -192). SAGE Publications, Ltd,
https://dx.doi.org/10.4135/9781849209939
iiiWong P. How to write resea rch proposal. International network on
Personal meaning. Available at www.meaning.ca/archives
Al-Riyami A. (2008). How to prepare a Research Proposal. Oman medical
journal , 23(2), 66 –69.
ivSudheesh, K ., Duggappa, D. R., & Nethra, S. S. (2016). How to write a
research proposal?. Indian journal of anaesthesia , 60(9), 631 –634.
https://doi.org/10.4103/0019 -5049.190617
vSaunderlin G. Writing a research proposal: The critical first step for
successful clinic al research. Gastroenterol Nurs. 1994; 17:48–56.
viKrishnaswami, Rangantham (2019) Methodology of Research in Social
Sciences, Himalaya Publishing House.
viiJohn W. Creswell (2019)Research design: Qualitative, quantitative, and
mixed methods approaches. Sage Publications.
munotes.in
Page 33
33 5
MAIN STEPS IN QUANTITATIVE
RESEARCH
Unit Structure
5.0 Objectives
5.1 Introduction
5.2 Inductive and Deductive Approach
5.3 Main Steps in Quantitative Research
5.4 Summary
5.5 Questions
5.6 References
5.0 OBJECTIVES
1.0 To understand the different steps involved in Quantitative R esearch
2.0 To learn about the ethics involved in these steps
5.1 INTRODUCTION
Modern Research in the market is increasingly being conducted as a team,
with each team member offering their specialised knowledge to the
project. Therefore, research activiti es have changed and has even become
highly competitive. Organizations, business and industry cooperate and
operate by applying mathematical and scientific techniques to solve
problems in theorganisation issues and through research studies. Corporate
bodies are also adopting research operations more and more to increase
productivity, management science research (OR) and methodologies to
improve quality and cut expenses. They use quantitative research to
address issues with planning, strategy, anddistribution of resources,
facility design, inventory management, employee schedules, and
distribution techniques. However, as students you will be conducting
independent research many a times, guided by a teacher.
Quantitative research focuses on collecting numerica l data and using it to
understand a specific event or generalise it across groups of
individuals.Quantitative methods place an emphasis on precise
measurements and the statistical, mathematical, or numerical analysis of
data gathered through surveys, polls , and other types of research, as well
as the manipulation of statistical data that has already been obtained using
computing methodsi.
In this chapter, you will be learning about the important steps which is
used in Quantitative Research. Learning these steps would give you a munotes.in
Page 34
Quantitative Social
Research
34 guideline, base, direction to undertake an independent study. This chapter
would act as a foundation chapter for the research methodology as the
topics dealt here would be spread across whole of this paper. Some topics
would be even common in this paper and you will also find it in the next
semester syllabus, i.e., in qualitative research too. Some steps are even
common if you are undertaking any research project or going for Higher
studies like PhD.
5.2 INDUCTIVE AND DEDUCTIVE APPRO ACH
Before understanding the main steps in detail, we need to first understand,
inductive and deductive approach. In Quantitative research many a times it
is the deductive approach used. While in Qualitative Research it is the
inductive approach used.
Inductive Approach
When a researcher takes an inductive technique, they start by gathering
information that is pertinent to their study topic. Here the researcher will
stop collecting data once a significant volume has been gathered in order
to step back an d gain a bird's eye view of their data. The theory is used in
order to account for the trends, the researcher also tries to find the patterns
in the data. In order to proceed from a specific set of experiences to a more
general set of propositions about ex periences, researchers use an inductive
approach. To put it another way, the researcher progress from facts to
theories, or from the particular to the general.
Deductive Approach
A convincing social theory will serve as the starting point for deductive
researchers, who use the theory first. In other words, they employ the
same procedures as inductive research but will carry out the processes
backward, going from broad to more precise levels. Scientific study is
most frequently connected with the deductiv e research approach. The
researcher analyses existing theories of the phenomena and then try to
examine, investigate what others have done, and then tests hypotheses that
result from those theoriesii.
munotes.in
Page 35
Main Steps in Quantitative
Research
35 Check Your Progress
1. What is Inductive approach
2. What is deductive approach
Steps involved in Scientific Research
Before getting into the details of Quantitative Research steps let us first
look into the Scientific Research steps.The steps of the scientific process
are:
• Choosing a study topic
• Review of pertinent literature to evaluate prior work in thechosen subject
for study;
• Compilation of statistics and facts already known about the subject of the
study;
• Creation of a well -thought -out hypothesis;
• Validating the idea in accordance with a careful study plan;
• Method and organisation of the data acquired for analysis;
• Reaching judgments and inferences;
• Generalization, provided the data support it;
• Assembling and presenting the research's findings;
Publication in peer review journals
5.3 MAIN STEPS IN QUANTITATIVE RESEARCH
1. Theory
As seen earlier Quantitative Research uses Deductive approach. Hence,
the existing theory is used to guide the research. Merriam dictionary
defines a theory as a plausible or scientifically acceptable general
principle or body of principles offered to explain phenomenaiii.
According to Byrman, the word "theory" has many various meanings,
its most common usage is to refer to an explanation for a n observable
pattern, such as why poor people fall more sick than rich people or why
job alienation differs by technology. There are several theories like
Grand theories, Middle range theories, Micro theories which exist in
social science. Grand theories a re those theories which are often
applicable universally and is generalizable to a large extent. For
example – Marxian theory of Class Struggle, concepts like Alienation.
These theories and concepts are applicable in every part of the world as
still the in dustries exists and the capitalists and working class are too
present, in addition the conflicts continue too remain in every society.
Another example is that of Functionalism. Middle range theories are munotes.in
Page 36
Quantitative Social
Research
36 like Robert Merton’s work, the micro theories are lik e
ethnomethodology, symbolic interactionism, phenomenology.
One can find theories in existing study, literature hence one has to look
into the studies conducted similar to one’s own research. A researcher
can use one or more theories in a given study. T he following are some
points to remember while reading -
Read a lot of reputable, pertinent reviews.
Recognize the study's variables
Create a list of synonyms or a replacement word
You can add variables to a Venn diagram while reading.
Keep citations compi led or located with abstracts
Read abstracts and remove any publications whichare not useful.
Determine whether you need to focus your review more or dig
deeper.
Systematically keep track of your pertinent readings
Read and made annotations on each pertine nt item
Organize and sort your annotations.
Created a draft of your proposed theories
Write with intention
You can use the literature to support your claims.
Use the proper diction and tone.
A clear understanding of literature on the topic and theories hel ps to figure
out the gaps in the research and that could turn out to be a research
problem for the study. Hence formulating the research problem is also one
of the main steps and first step of doing quantitative research. A clear
research problem helps the investigator to understand what is the problem
and what he/she wants to find out about the problem. Hence to do that,
literature survey could be carried out through visiting libraries, studying
existing research papers on the same topic, referring to arti cles on internet,
reading several thesis on similar topic, discussing with people working on
the same area.
2. Hypothesis –
According to Collins Dictionary - A hypothesis is an idea which is
suggested as a possible explanation for a particular situation or condition,
but which has not yet been proved to be correctiv.In quantitative
investigations, a hypothesis is typically put forth before the study and
tested later on. Having a predetermined hypothesis helps researchers focus
their investigation and interpr et the findings in light of a pre -existing
theoretical framework. A hypothesis is developed based onexistent
knowledge which is a tool for advancing knowledge through testing it
throughout a research investigation and haveknowledge about a specific
topic. In the event that a certain hypothesis is found to be false during a
study, still theoutcome is considered a knowledge breakthrough since we
are aware that within the context of the investigation,The listed factors munotes.in
Page 37
Main Steps in Quantitative
Research
37 have a relationship or not. This could al so benefit other scholars who
might be studying similar studies in the futurev.
3. Research Design
Research Design is the blue print of the study. A lot of decision -making
goes into research design. It gives your researcha framework and
direction. Follow ing the selection of your topic, one has to make a
decision regarding the methodology which will be used in research. It
entails developing a strategycovering all phases, from the creation of
hypotheses to the data analysis here the research design helps. According
to Kerlingerresearch design is a strategy, framework, and blueprint for an
investigationas well as to find solutions to issues or challenges in study. It
comprises an outline of the different steps the researcher will take, starting
with drafting the hypotheses and their operational implications all the way
through to the data analysis at the end. According to Thyer, a research
design is a precise strategy or blueprint for a studyoperationalizing
variable in a study so they may be quantified, to c hoosinga study sample,
gathering information to use as a foundation for testing theories,and
finally, reviewing the outcomes. There are different types of Research
design like descriptive, experimental, exploratory etc. munotes.in
Page 38
Quantitative Social
Research
38 A research question is an inquiry t hat makes clear what the researcher
specifically wants to know. A research question forces the researcher to
be more specific about what is to be examined. A research purpose might
be stated as a statement, such as "I want to find out whether (or why). A
research question cannot exist without a question mark at the end of it. In
other words it must be a question.
A list of different kinds of research questions has been offered by
Denscombe (2010). This list first appeared in an older edition that White
has updated (2009). Denscombe suggests the following categories of study
questions:
1. Making predictions (does x occur under conditions a and b?).
2. Defining the causes and effects of an event (is y a result of x or an effect
of x?).
3. Assessing a phen omenon (does it demonstrate the benefits that are
asserted to exist?).
4. Describe the phenomenon (what does it look like or take on?).
5. Establishing positive habits (how can we do y better?).
6. Empowerment (how can we make those whose lives we study better?)vi.
4. Concepts
A concept is an abstract word that unites various meanings. Concepts
occasionally appear in the field. A researcher should choose the main
concepts from the problem studied. The concepts used in the particular
hence has to be clearly defined. As it carries different meaning outside the
context too.
5. Selecting the Research Site
A research site is the location in which the research is going to carried out.
This takes time and effort too. A pilot study helps to understand whether
the chosen site is helpful for the study or not. While choosing a research
site one has to remember bothtime and money.
6. Selection of Respondents
Selection of the respondents has to be based on the research problem,
topic. There should be proper representati on of the sample. Rapport
building helps in choosing the sample easily. The respondents need to
have proper representation of age group, class, location, caste, gender.
7. Data Collection
Data collection can be carried out at different stages or at one tim e too.
Tools like Survey even help in carrying out studies through online. munotes.in
Page 39
Main Steps in Quantitative
Research
39 However, the response rate of online survey might differ specially if the
questions are lengthy. However, large scale studies like Census involves
door to door collection and it tak es years to complete and also requires
large amount of field investigators. Reliability and Validity are very
important while conducting any research. Stable, reliable, and dependable
research methods, tools, data, or outcomes are characterised by reliabil ity.
The crucial quality of the entities, processes, or tools are used to measure
the various aspects is validity. Objectivityand subjectivity are traits that
have an impact on the research findings in hence one has to be cautious
about it. Subjective pers onal bias may spoil research findings. Hence one
has to be very carefulvii.
While collecting the sample one’s own bias should be avoided completely.
This would help in gaining maximum precision and accuracy of the data
generated.
Sampling methods like ra ndom/ probability/mixed/ non random sampling
could also be used.
8. Data Processing
Data management –Data can be stored in proper software. However,
there are other steps like routinely logging in and screening your data,
entering the data into a programme , and lastly "cleaning" your data.
Understanding variable types - Different data kinds call for discrete
treatment, so it's crucial to look into variables by their measurement
scales and both their causes and effects (dependent or independent)
(nominal, o rdinal, interval, and ratio).
One also has to run descriptive statistics to identify the key
characteristics of a data collection. These statistics include measures of
central tendency (mean, mode, and median), dispersion (range,
quartiles, variance, and standard deviation), and distribution (skewness
and kurtosis).
There needs to be proper inferential statistics in order to evaluate the
researchers' capacity to make inferences that go beyond the data at
hand. A sample representing the population, differe nces between two
or more groups, changes through time, or a relationship between two
or more variables also helps.
Make sure you use the appropriate statistical test - this depends on
understanding the nature of your variables, their scale of measurement,
their distribution shape, and the types of questions you wish to pose.
munotes.in
Page 40
Quantitative Social
Research
40 Be on the lookout for statistical significance. This is typically
represented by a "p -value," which determines the likelihood that your
findings are not just a coincidence. Researcher s can be more certain
that results are real the lower the p -valueviii.
9. Data Analysis
In order to determine if one variable significantly affects another, the
researcher use a variety of statistical approaches to search for significant
correlations between v ariables.The simplest technique is to arrange the
relationship between variables into graphs, pie charts, and bar charts.
These tools are essential for communicating the findings of one's
quantitative data analysis to others and provide an immediate, "intu itive"
visual impression of whether there is a significant relationship. Even codes
are used to make the analysis simpler. Data Analysis takes more time at
times even more than data collection. As writing is an art which is shapes
with time.
10. Findings
The researcher must evaluate the analysis' findings in light of the data
analysis. The results will become apparent at this point, including if the
hypothesis was validated. What consequences do the findings have for the
theoretical concepts that served as th e research's foundation?This has to be
kept in mind. Often Scientists frequently collaborate with one another and
discuss their discoveries. As a result, hypotheses are frequently updated,
improved upon, or replaced. As a result, knowledge doubles every fi ve to
ten years in some areas of science. The proof that science is a useful tool
for discovering new things can be seen through research. As all around us,
knowledge is expandingix. The interpretation of the results is also an
important thing which has to be carried out while reporting the findings.
In some disciplines and among some universities certain research also
provide recommendations and suggestions and limitations of the present
study and there is further scope in which the study could be carried out
while reporting the present finding. The findings also highlight
theuninvestigated areas which other research could carry out as an
extension of the present research. After all research is a collective effort
and scholarship.
11. Publishing Results
Once the study is completed, the data could be summarized and published
as journal articles, books. At times, the research is also presented in
conference. It is also quoted and cited by other scholars. If the paper is
bringing about a social change or solving a problem, even policy makers
make use of such research. The researcher also can visit and share the
findings with the subjects upon whom the research was conducted. This is
also part of knowledge sharing process which would help develop trust
and even the community to understand their own lives from a third munotes.in
Page 41
Main Steps in Quantitative
Research
41 person’s perspective. However, this has to be carried out with certain
degree of caution specially in topics like gender, caste, violence etc.
Ethics and Legal requirements
Laws apply to everyone, even researchers. It is forbidden for researchers
and research subjects to do anything that is forbidden for the general
population ill health or harm. However, researchers who: (a) desire to
explore illegal activities; or (b) come across criminal activities w hile
conducting their investigations face a more typical legal conundrum. The
courts can demand your data and files in most nations, you are required to
disclose illegal activity. Researcher assurances of secrecy may not be
upheld in court, according to le gal precedence. You do not have the same
rights as a lawyer, doctor, or priest as a researcher in several countries
hence, one has to be careful.
Moral responsibilities
Some moral factors one has to take into account when conducting
research:
One has to b e conscious in prioritising the needs of respondents or
participants.
There needs to be Equity while studying and asking some demographic
groups to participate in research while leaving other groups off -limits.
Honesty is the need of the hour and researche rs need be forthright and
truthful as well as that results in the specifics of the research process be
made transparent.
The professional code, the discipline, and the institution will all have
different ethical standards for research conduct, they need to be consulted
when in doubt.
A participant can only offer "informed consent" to participate in a research
study if they fully understand the request for their engagement, including
the time commitment, type of activity, topics that will be covered, and th e
potential physical and emotional hazards involved. Participants must be
competent, autonomous, willing to participate willingly, aware of their
right to withdraw, not duped, not pressured, and not induced in order to
give their informed consent.One has t o make sure there is no physical,
emotional, or psychological harm suffered by respondents.
Protecting the identity of persons who provide research data; all
identifying information belongs to the researcher alone; ensuring
confidentiality and, if necessar y, anonymity. Beyond confidentiality,
anonymity refers to safeguards against identification, even by the
researcher. This has to be done specially in sensitive topics.
munotes.in
Page 42
Quantitative Social
Research
42 Check Your Progress
1. Explain hypothesis in few lines
2. Discuss measures to take w hile selection of respondents
5.4 SUMMARY
Quantitative research focuses on collecting numerical data and it is used to
understand a specific event or generalise it across groups of
individuals.Quantitative methods place emphasis on precise measurements
and the statistical, mathematical, or numerical analysis of data gathered
through surveys, polls, and other types of research, as well as the
manipulation of statistical data that has already been obtained using
computing methodsx. Further, in the chapter w e also learnt about the main
steps associated with Quantitative Research. The main steps are Theory –
Hypothesis, Research Design, Operational Concepts, Selection of
Research Site, Selecting Respondents, Data Collection, Data Processing,
Data Analysis, Fin dings/ Conclusion, Publishing Results. We also learnt
about Inductive and Deductive approach used in research. Inductive
approach is often used in Qualitative research while that of Deductive
approach is used in Quantitative research. In Inductive approach Data is
gathered then patterns are formed and thereafter theories are used. On the
other hand, in the Deductive approach the theories are used first and
through that the research is further guided and conducted and hypothesis is
tested accordingly in the research. One of the important steps in the
present times while doing Quantitative or Qualitative research is that of
remembering the ethics while conducting research. There are even
Research Ethical committees who go through the proposal before the
resear ch begins.
5.5 QUESTIONS
1. Discuss the main steps involved in Quantitative research
2. Explain the ethics and legal requirements while conducting
quantitative research
3. Discuss the inductive and deductive approach in quantitative research.
5.6 REFERENCES
iBabbie, Earl R. The Practice of Social Research . 12th ed. Belmont,
CA: Wadsworth Cengage, 2010; Muijs, Daniel. Doing Quantitative
Research in Education with SPSS . 2nd edition. London: SAGE
Publications, 2010.
iihttps://scienti ficinquiryinsocialwork.pressbooks.com/chapter/6 -3-
inductive -and-deductive -reasoning/
iiihttps://www.merriam -webster.com/dictionary/theory
ivhttps://www.collinsdictionary.com/dictionary/english/hypothesis munotes.in
Page 43
Main Steps in Quantitative
Research
43
vhttp://epgp.inflibnet.ac.in/epgpdata/uploads/epgp_cont ent/social_work_e
ducation/05._research_methodology_and_statistics/08._hypothesis_and_re
search_questions/et/6056_et_et.pdf
viBryman, A. (2016). Social research methods . Oxford university press.
viihttps://egyankosh.ac.in/bitstream/123456789/11204/1/Unit -1.pdf
viiihttps://study.sagepub.com/oleary3e/student -resources/analysing -
data/steps -in-quantitative -analysis
ixL Mitchell, M., & M Jolley, J. (2010). Research design explained .
Creswell, J. W., & Creswell, J. (2003). Research design (pp. 155 -179).
Thousand Oaks, CA: Sage publications.
xBabbie, Earl R. The Practice of Social Research . 12th ed. Belmont,
CA: Wadsworth Cengage, 2010; Muijs, Daniel. Doing Quant itative
Research in Education with SPSS . 2nd edition. London: SAGE
Publications, 2010.
munotes.in
Page 44
44
6
WRITING RESEARCH REPORT
Unit Structure
6.0 Objectives
6.1 Introduction
6.2 Meaning of Report Writing
6.3 Types of Report
6.4 Functions of Research Report
6.5 Format of Research Report Writing
6.6 Tips for writing Report
6.7 Summary
6.8 Questions
6.9 References
6.0 OBJECTIVE S
To learn the meaning of Research Report
To understand the process involved in making a research report.
6.1 INTRODUCTION
In this chapter, we will learn about what is research report and what are
the steps involved in writing a good research report. This chapter would be
an important study material in terms of career view point. For example -
After your graduation if you are interested in working with a Non -
Governmental Organisation or with a Human resource management – you
are often expected to write rep orts. This could be about a field visit, about
a project. After studying a particular company, problem, field or even after
completing a project. Hence, learning about this topic becomes very
important. A good report can help you get funding too. Companies hires
people or even outsources the work to freelancers too to write reports.
In terms of companies before introduction of any introducing a new
service, product, or feature, research is essential. Due to the daily influx of
new competitors and speed of p roduction research is needed to find out the
gap in the products, markets. Even for a firm to remain relevant in
competitive market it has to be updated with new products that meet client
requests. They also have to make the appropriate decisions must be m ade
at the right time. Hence, these corporates also need people who conduct munotes.in
Page 45
Writing Research Report
45 research and produce reports. Even PhD, MPhil students are expected to
submit six month or every month progress report to show their progress.
The four core documents in any resea rch are that of the research proposal,
research summary, research abstract, and the research report —all these are
used to evaluate the appropriateness, quality, and validity of every
research/study. Among all these the primary document used to assess the
contribution of the research is the research report. The process of
conducting research includes multiple stages and a flow of documents.
The order and stages of the process have a real impact on the quality of the
final report and the research materials cr eated at every level.
6.2 MEANING OF REPORT WRITING
A research report is an official, formal declaration that includes facts,
provides a record of findings, and/or could be the outcome of a survey or
study (Booth 1991). The Oxford English Dictionary defi nes a report as a
declaration of the findings of an inquiry or of any subject requiring
specific information.
Report writing can be done for a variety of reasons, including: presenting
findings; maintaining records of the information/data gathered; and
• In order to record an organization's accomplishments and shortcomings
• To document the development of a project or research in writing.
Research reports are written statistics that are created by statisticians or
researchers after information has been coll ected through organised
research, generally through surveys or other qualitative approaches.
Reports typically include a wide range of subjects, but they are primarily
concerned with disseminating knowledge on a single subject and a
relatively specific tar get audience. The main goal of research reports is to
offer crucial information about a study that marketers can take into
account when developing new tactics. The most efficient method of
communicating certain incidences, facts, and other information to t he
decision -makers is through writing research reports. The best research
papers contain material that is incredibly accurate and have a clear
purpose and conclusion. These reports must be presented in a clear,
organised manner if they are to effectively c onvey information.
A research report is a trustworthy source to retell specifics about a
research project and is frequently regarded as a true testament to all the
work put in to gather research specifics.
One can find different sections in research like t he Overview, Introduction
and Background, Applied Techniques, Findings from the analysis,
Discussion.
While many of the components and portions of report writing are generic,
it is distinguished by certain themes that are unique to it. Reports are
writte n using factual material supported by statistics and findings. The munotes.in
Page 46
Quantitative Social
Research
46 authors' own biases or sentiments should not have any bearing on the
material, which means the research report has to be objective in nature.
Report writing is an art which has to be culti vated. It has to be tailored
according to audience needs. For example – If the report is submitted to an
academic institution it has to bedesigned differently focussing more on
theory, methodology, literature application of theories and the findings
and fo llowing the format given by the institution. On the other hand, while
writing a research report for business project the length can vary from
small to big. It often focusses on the study area, field details, key
methodology used, findings of the topic. Res earch Report connected to
Social Policies or an investigation related to schemes, its effects, benefits
also at times includes the recommendations at the end of the report. As
here researchers are trying to solve the problem too than just studying it.
Depending on the goal of the research, the financing or sponsoring
organisation, the report has to be altered. The field workreports can be
divided into a number of different categories. Reports, such as those on
budgeting and other organisational tasks, migh t be very brief and concise,
and it can be published for informational purposes. Another kind of report
writing that is frequently used in universities for project documentation are
case studies and analyses. An informal format may be used for a report
intended for an organization's internal audience. If a report is discussing
topics like absenteeism, work plans, or processes, an informal
conversational tone may be appropriate. In a report which is written for an
employee policy, a manual, or a task report, might be casual, semi format
language but can still have a defined framework. The third is a formal
report that has a specific format and organisation as well as sections for
research, analysis, and also draws inferences.
6.3 TYPES OF REPORT
1. Technical Re port
This is a detailed report on the entire study process and its findings. It is
mostly targeting the academic community. For example, the scientists and
researchers. The technical report's focus and even the language are both
primarily technical in nat ure. Like in every other report, the problem is
explained, the method(s) and techniques employed are described, along
with the results and recommendations.
2. Popular Report
In this kind of report there are more headlines, italicised text, images, and
concis e phrases in this report. To catch the reader's attention, there is
white space and extra margin. This report is built like a journalistic
writing. The style encourages the reader to have quick reading and
comprehension of the topic and finding.
3. Interim Report
This report is essentially a work in progress. It describes how much work
has already been done and what remains. If the report is a funded project, munotes.in
Page 47
Writing Research Report
47 then the Interim Report is used. These aids the sponsors in maintaining
their enthusiasm and poten tially continuing the funding. Additionally, it
displays the analysis and results up to this point.
4. Summary Report –
This kind of report is written for the general public or lay readership.
There are no jargons or technical terms in the language. It is
straightforward and explains everything with many images and graphs.
The reports often only have two or three pages (Krishnaswami,
Ranganatham, 2019).
Check Your Progress
1. List out two types of Report.
2. Explain your understanding of Reference
6.4 FUNC TIONS OF RESEARCH REPORT
1. The research report provides a way for organising the presentation of
the topic under investigation, the approaches and methods utilised for
gathering and analysing data, the conclusions, and the suggestions.
2. The research re port provides as a foundational resource for creating
research projects in the same or related fields in the future.
3. The research report is used to assess the calibre of the finished study
job.
4. The research report serves as a tool for assessing the r esearcher's
capacity and expertise to do research
5. The research report offers a factual foundation for developing policies
and strategies related to the topic under study.
6. It offers organised knowledge about the themes and problems analysed.
6.5 FORMA T OF RESEARCH REPORT WRITING
The specifics of a research report may alter depending on the goal of the
study, but the fundamental elements will always be present. The market
researcher's method of conducting research has an impact on how reports
are writte n as well. The following are the top seven elements of an
effective research report:
• Research Report Summary: The first thing a research report consists is
a summary/ Abstract. In a business research report – the title used is
executive summary instead of summary. The research report summary
consists of few paragraphs. Itshould incorporate the complete purpose as
well as an outline of the research. Under the report summary, each of the
research's numerous components is briefly discussed. It ought to be
captivating enough to include all the essential aspects of the report. when
PhD students write an abstract in the beginning pages of the thesis. This munotes.in
Page 48
Quantitative Social
Research
48 abstract explains the objectives, methods used, and overview of the thesis
and findings. This helps the exami ner/ readers to the get the core idea of
the thesis.Unlike when we read the Newspaper title and the first paragraph
we get an idea of the content of the article in the same way, the research
report summary acts.
•Research Introduction
Every report has a m ain objective that the author is seeking to accomplish.
These objectives are listed out in the Introduction section of the project. In
the Introduction the researcher can discuss goals pertaining to this
objective in the introductory part and formulate a t hesis that will be used
to try and provide a thorough response. What is the goal's present
situation? should be addressed in this paragraph. Provide such information
in the research report's opening section. Did the researcher successfully
complete the goa l after the research was completed, or are they still a work
in progress? Here the discussion theories used in the research is also made.
This is done to produce an interconnection between existing studies and
that of the current study. It also creates cre dibility and shows the research
gap of the existing knowledge.. However, theories are not a must in the
works which are presented for business reports. Here, the limitations of
the study are also discussed in detail. The introduction part of the report
also by using different examples and arguments, prove the problem's
existence; arouse interest in your work by highlighting its relevance and
significance; name the key problems; and give context for your proposed
solution.
• Methodology
The most signific ant information is located in this portion of the report.
Readers can learn more about the subject while also evaluating the quality
of the content given. As a result, this section must be extremely
informative and cover every facet of the research in dept h. Information
must be presented chronologically in accordance with its value and
priority. As a result, this section must be extremely informative and cover
every facet of the research in depth. Information must be presented
chronologically in accordance with its value and priority.If a researcher
used an established technique to obtain information, they should cite their
sources. This section explains what was done during the study, where it
was conducted and what was the procedure followed, tools, techni ques
used, the number of people participated or studied.
Who are the subjects, in (a)? The study's subjects are described in the
subsection Age, gender, and other pertinent social or demographic factors
are used to describe the subjects. (b) The number of subjects. Mention the
overall participant count as well as the split by experimental condition. If
any subjects chose not to finish the study, please list their number and the
reason. (c) How are the subjects chosen? Describe how the volunteers
were chose n for the experiment and how they were divided into groups.
Was a randomization methodology employed, for instance, or was a munotes.in
Page 49
Writing Research Report
49 different approach required? Report any promises or payments made to the
subjects (Kabir, 2016).
Research Results -
In this sectio n the results are discussed. A summary of the findings as
well as the methods used in order to accomplish the objective. Usually, the
report's discussion section is where the description follows data analysis.
Research Discussion -
Here the findings are covered in great length in this section, which also
includes a comparison of papers that might be in the same field. In the
discussion area, any irregularity found during research is also discussed in
detail. The researcher also needs to make associating w ith existing
literature, studies and explain when they write study reports about how the
findings will be applicable in the real world.
References for the research and its conclusion -
Here the researcher has to summarize the research findings and include all
authors, articles, and other content sources consulted.This final part should
follow APA formatting guidelines. The term references should be at
included as subheading at the end of the project; it should not be
underlined or included in quotation mark s. References cite works that are
openly accessible. The page number can be included, especially if it’s an
article. Reference lists of works cited in your text are required, and the
details of it has to be given at the end. = Reference lists must be accur ate
and comprehensive because they are meant to be used by the reader. The
following general subsections make up a reference: Author, Year of
Publication, Title, Publication Place. If the work is taken from Edited
Book that that has to be mentioned too.
6.6 TIPS FOR WRITING REPORTS -
A well written report helps the readers to understand the content very
easily. The followings are some pointers through which one could write
better research reports:
Research Reporting writing becomes easier if one is organi zed. For
drafting research reports, the arrangement of the survey questions may not
be the best or most efficient. The goal is to begin with a wide issue,
narrow it down, and then concentrate on a conclusion or support that the
study should provide evidenc e for.
Starting a report takes time and effort and motivation too. Hence, taking
slow steps towards the goal of writing helps. Begin with the title and
introduction. While choosing a format, keep the target audience in mind
and make sure it is simple, comp rehensible, and relevant. If the report
would be viewed by policy decision -makers then write it accordingly. Be
consistent in the language you use, the annexes' numbering, and other
areas. munotes.in
Page 50
Quantitative Social
Research
50 Follow the institutions guidelines for the delivery of research fi ndings, and
ensure that the project has covered the objectives of the study. Before
submitting a researcher needs to read the entire proposal and confirm that
the information, they provide supports the goals that were outlined at the
outset. If a researche r speculates, they are directly challenging their own
research.
Obtain all the data you can on the study, subject. Speak with other
researchers who have studied the similar problems and familiar with the
terminology used in the field. When terminology is misused, readers of
research reports may become less interested in continuing to read aloud
while writing.
Read the report loudly and check if there is any error. If the you an
improper sound while reading the report, for instance, if you misread some
word s, the reader will undoubtedly experience the same thing. If the
researcher can't express an idea in a single sentence, then it is too long and
needs to be changed so that everyone can understand it. Check your
spelling and punctuation. Good practises unqu estionably aid in
comprehension of the report. Utilize present tense, verbs. Consider
utilising the present tense to sound more immediate with your results.
Avoid using jargons, slangs.
Explain mainly about the significant findings. Do not mention any data
that are not very important. Make an effort to stick to the survey's
questions. The graphs need to be easy to grasp by themselves. Give the
graphs a title, including the indicators, the size of the sample, and the
appropriate phrasing to prevent readers f rom misreading them. Every
portion of the report should be written by the researcher with correctness
in both language and details.
Use proper titles which suits the content of the topic, especially for
segmentation studies. Use namesthat add life to study .Write a effective
conclusion. The research report's conclusion is the hardest to write, but it
also presents a fantastic opportunity to shine. Write a thorough synopsis. It
can be helpful to begin the conclusion with a specific statement, followed
by a s ummary of the most significant findings from the study, and finally a
discussion of any ramifications. It's challenging for writers to spot their
own errors. However, they are in charge of what is displayed. Before
sending the final document, be sure it ha s received the approval of the
supervisor, teacher in charge of the report.
If there is an earlier report already submitted then we have to inform the
reader/ sponsor about what are the new things being included or show the
continuation of it too. Howeve r, one has to include some background
before describing the content of the present proposal.
munotes.in
Page 51
Writing Research Report
51 Check Your Progress
1. List out two important points to remember while writing Research
Report
2. What does Research Results means in Research Report?
6.7 SUM MARY
Report writing is a laborious task since it entails compiling and presenting
all the information gathered during field research in accordance with a
predetermined research strategy. Writing a report requires a very
structured style, which takes time. We also saw in the chapter that there
are different types of reports like Interim Reports – which discusses the
work in progress, Technical report in which we uses technical information,
jargon and caters the scientists and researchers than general public .
Conventions have been established to create a standard format suitable for
readers and/or audiences. The format and convention of written reports
often emphasis on the method used to obtain the data necessary to produce
the report.In conclusion, we can c onclude that a research report is an
authoritative, narrative document that summarises the findings of a
research project. It offers incredibly detailed information to a very
specialised audience. Its communication style is unpersuasive. The subject
being delivered comes first, followed by presentation. It is an easy -to-read,
precise style of communication.A well -written research report provides an
organised way to convey the examined issue, the data collection and
analysis procedures, findings, conclusions , and suggestions.The intention
of the research report is to express the core ideas.
6.8 QUESTIONS
1. Discuss the meaning of Research Report
2. Discuss the different tips while writing research report.
3. Write the different types of Research Report and the func tions of
research report
4. Discuss the format for Research Report
6.9 REFERENCES
1. Bryman, A. (1988). Quantity and Quality in Social Research. London:
Routledge
2. Bryman, A. (2008). Social Research Methods. Oxford University Press
3. Matt, H., Weinstein , M., Foard N. (2006) A Short Introduction to Social
Research. New Delhi: Vistaar Publications
4. Goode, W., Hatt, P. (1981). Methods in Social Research. McGraw -Hill
Book Company
5. Somekh, B., Lewin, C. (ed) (2005). Research Methods in the Social
Scienc es. New Delhi: Vistaar Publications munotes.in
Page 52
Quantitative Social
Research
52 6. Krishnaswami O.R., Rangantham M, (2019), Methodology of Research
in Social Sciences.
7. Datar A, Nicosia N. Junk Food in Schools and Childhood Obesity. J
Policy Anal Manage. 2012 Spring;31(2):312 -337. doi:
10.1002/ pam.21602. PMID: 23729952; PMCID: PMC3667628. This
article can be used as a sample for research report. As some points are
relating.
8. Kabir, Syed Muhammad. ( 2016). WRITING RESEARCH REPORT. In
book: Basic Guidelines for Research: An Introductory Approach for
All Disciplines (pp.500 -518)Publisher: Book Zone Publication,
Chittagong -4203, Bangladesh
munotes.in
Page 53
53 ASPECTS OF QUANTITATIVE RESEARCH
7
SURVEY METHOD
Unit Structure :
7.0 Objectives
7.1 Introduction
7.2 Meaning and Definition
7.3 Aims of Social Survey
7.4 Types of Survey
7.5 Methods of study
7.6 Advantages
7.7 Disadvantages
7.8 Summary
7.9 Check your progress
7.10 References
7.11 Questions
7.0 OBJECTIVES :
To understand the term survey as a means for collection of data or
information.
To study survey as a process by which quantitative facts are
collected.
To familarise the students with the organisation of survey is a
important form of data collection.
7.1 INTRODUCTION :
The word survey has been derived from the word ‘Sur’ and ‘Veeir’ which
mean ‘over’ and ‘see’ respectively. Literally survey means something
taken from a high place but it has come to be used as a term with
specific purpose of its own. In other words the term Survey is used for
method of investigation by direct observation of a phenome na or getting
information theory interview or questionnaire thus the term survey is not
applicable to direct contact but also to the other means say for collection
of data or information. munotes.in
Page 54
Quantitative Social
Research
54
7.2 MEANING AND DEFINITION :
The Survey is defined as fact finding study dealing chiefly with working
community.
According to mark Abrams” a social survey is a process by which
quantitative facts are collected about the social aspect of community
composition and activities from the above definition.
It may be drawn the characteristic feature of a social survey. It is a story of
immediate and burning problem of the social and constructive programme
of social research for remoxing the social evils the scope of its limited and
localized geographically. And it may from the basis of for further social
research on the matter. In brief, the social survey is designed the
investigate some course relationship of the some aspect of human lif e. A
social survey is to perceive with the aims given below.
7.3 AIMS OF SOCIAL SURVEY :
1) As we know that the survey will become a basis for further
investigation. Supply of information to needs one is it main objective.
The needy one may be an institutio n or individual thus survey is utilitar ian
in nature and meant of provide information regarding the practical
problems of the society. A researcher of himself may carry out survey s but
there are some agencies that carry survey for other.
2) Survey describe th e phenomena to a social scientists a survey may
have descriptive as a way of studying social condition, relationship and
behaviour for example survey communities. Socio economic survey
describes the living condition of people of a geographical area. The
description would be accurate as well as complete if we became to face
with it. Further the purpose of the social survey is to get information and it
is not meant to test an hypothesis but simply describe the things therefore
survey may be started without any hypothesis the description of data. So
collected may serve as a basis for hypothesis later on.
3) Alongside of the description, the social survey explains the
determinants for the state affairs may be so specific and purposive.
Social survey has intensive usage and is widely used in a number of
disciplines. In social sciences it can be used for variety of purpose
availability of nature of the source of information is the main and source
of undertaking a survey. Broadly the subject matter of social surveys are
divided into
1) Demographic Features
2) Social conditions
3) Opinion and attitudes
Demographic features come under the purview of organisation and munotes.in
Page 55
Survey Method
55 working of family regarding such information as household composition,
marital status are family planning programm es etc. the social conditions to
which people are subjective this includes occupation, incomes, a housing
amenities many of social action as conditioned by the social condition i.e.
Social environment in which people live. So social condition are helpful t o
get the following information and there upon to establish the casual
relationship to study the family relation. One would require information
on the location the extent of relationship with elders etc. a survey of
deliquenets would in complete unless. Following knowledge of their
homes and family environment is available.
Social activities such as expenditure pattern, radio listening newspaper
reading social mobility information for example to know the expenditure
putter of a group of family house. It req uires to the survey or following
knowledge on expenditure habit say, expenditure towards family, clothing,
education, cigarettes, cinema and other.
Opinion and attitude , includes information regarding opinion and
attitudes of the people toward various fact or and the motives and the
expenditure of them this information may be necessary as the basis of
nature of question that may safety be asked for electing rich response. For
eg. The opinion or attitude person toward social economic political,
incident surve y.
7.4 TYPES OF SURVEY :
a) General or Specific Survey
b) Regular and Adhoe Survey
c) Preliminary and final survey and
d) Census and sample survey
The general survey concerns with collecting general information about
population institution or phenomena with out any specific object or
hypothesis. The types of survey are mostly taken by the government for
providing regular data on may socio economic problems. A good example
for this surveys is census of population once in a decade. Any it is termed
as specific survey information collected through the specific survey is
general of very little outside the problem under study. For example,
marketing survey on a particular issue, say people, attitude about the use
of television.
Regular survey is survey conducted at regular intervals. To this permanent
machinery for collecting information is to be set up. Many of such surveys
are mainly economic surveys. For example, a study of family budget can
be cited as example. Another example is the rural credit survey of the
Reserve Ban k of India which collects data regarding the rural conditions
annually. munotes.in
Page 56
Quantitative Social
Research
56 Adhoc Survey is undertaken for all it may be conducted in phases if the
area of investigation a large. Because of completion of survey in phases
due to its largeness, it never initials as regular or repetitive survey. A
preliminary survey is one which is to be undertaken well in advance to get
the hand knowledge of the universe to be surveyed. Further, it helps the
survey or to get acquaint himself with the nature of the problem so that he
can be able to get the rich response. After conducting the preliminary
survey only, the construction of schedule or questionnaire may be taken
into picture. And it also guides the way of planning as well as organizing
The preliminary survey may also be called as A pilot studying which is
conducted well before taking a detailed study about the main work. After
the pilot study has been completed from the final survey is made.
Every unit is the universe is to be contacted and data collected from it
called census survey while a few units of the universe covered it refers to
sample survey. Planning of a social survey : the quality of survey results
to be considerable degree on the preparation made before the survey is
conducted so planning a survey is of paramount importance in social
sciences. The researcher has to give careful and conductive though out the
planning of a survey. Planning of social research programme must for its
successful execution part on remarked that only be carefully planning the
survey from start to finish can reliance be place upon results and in many
cases will the finding ever rich the publication stage therefore it is
pertinent to think twice properly at the planning of a social survey with
regards to the following points. Scope of the survey : next to the purpose
of survey, scope of it is important step regarding to the type of
information, subject matter, geographical area. For instance, an enquiry
may reliable to India or a particular style or an industrial level town or a
partic ular industry in particular location .
7.5 METHOD OF STUDY :
The method of study : in selecting a particular method for a survey. The
researcher should take the consideration of its suitability and has own
knowledge of it.
Unit of data collection and the u nit or units of universe must be clearly
defined for the purpose of an enquiry before taking the task of collection
information. However, defining the units is not as simple as it appear to be
for eg. to study the size of a mill we have different oriteria of measuring
the size of a small such as capital employed number of employees
production etc. for efficient collection of information the unit of data
collection should have the characteristic which are as under.
a) the purpose of enquiry being studied to the unit.
b) the unit should be specific.
c) the unit should be stable in character.
d) the unit should be uniform though out the report. munotes.in
Page 57
Survey Method
57 Sources of Data :
After the purpose, scope and methodology have been defined clearly and
properly the investigator has to plan abo ut the sources of data the sources
of data may be either primarily or secondary. Either the two devices or
only one device to be used in the investigator may be depended upon the
objective and purpose of the survey . Quite often in social sciences
investiga tion both may be used mode of data collection of social
phenomena is very complex and influence by a number of variables.
Therefore, it is essential to decide hand what type of information is to be
collected adopting the questionnaire or schedule.
Organisa tion :
Organisation of survey is very much important from the point of getting
quantitative as well as qualitative data. A number of field worker may be
require d and training must be given to them if necessary. Arrangement
with regard to checking and super vision should be made so as to avoid
giving false information. Editing and coding if needed have to be
undertaken . Following it classification and analysis of data has to be
carried out. All this organisation work should be pre planned.
Report :
After the data have been classified and analysed the next step in a survey
is to be drafting the report to whom it meant determines the style of
presenting the report.
7.6 ADVANTAGES :
The following advantages have with the survey method in
compensation to other method s they are :
1) The researcher comes in contact with the people whom he wants study.
And with this he can observe things personally with relaties and there
upon his inferences are not based upon any other theory or dogma till
upon the fact of the life.
2) The su rvey method leads is greater objectivity many field worker use in
the survey remove possible faios and collect correct information .
3) Survey may very well lead to the introduction of new theory for
example poverty was regarded as the course of crime for fai rly long
time till increasing crime in advanced countries have falsified this
theory.
4) Survey method enables to have fill knowledge of social institution.
The actual experience with the situations amounts none to any amount
of investigation.
munotes.in
Page 58
Quantitative Social
Research
58
7.7 DISADVANT AGES :
1) For carrying the survey field workers are to be recruited and training is
to be given to them. All this need for money.
2) It is a prolonged and time consuming process.
3) The reliability of the data collected through survey is not always
without doubt, h onestey and efficiency of the field -operation of the
respondents the suitability of schedule etc. Paramount for collecting
valuable data. But all these requirement are very seldom and the data
collected may obtain invalid data.
4) Survey is conducted on samp le basis and therefore it is subject of the
sampling error.
7.8 SUMMARY :
A social survey in its broder sense, has a reference to a first hand
investigation analysis and co-ordination of economic, sociological and
other related aspects of a selected commun ity group. A survey may be
undertaken with the primary purpose of a selected community or group.
A survey may be undertaken with the primary purpose of formulating a
programme for amelioration of the conditions of life and work of a
community or a group, implying some frame in the mind of the survey or
as to what the conditions ideally ought to be. The purpose of a social
survey may also be used to provide scientifically gathered facts or
materials affording some empirical basis for the social theorist to set up
their conclusions.
7.9 CHECK YOUR PROGRESS :
1) What do you mean by Survey?
2) Discuss aims of Survey Method.
3) Explain various types of survey method.
4) Highlight advantages of survey.
5) Analyse disadvantages of survey.
7.10 REFERENCES :
1) Wilkinson and Bhanden kar : Methodology and Techniques of
Social Research, Himalaya Publishing House, Mumbai 1977.
2) Denzine N. K. and Lincoln, Y. S. (Eds) Handbook of Qualitative
Research, London Sage Publications 1994.
3) Bryman A; Quantity and Quality in Social Science Research, London munotes.in
Page 59
Survey Method
59 Routledge 1988.
4) Dillon W. R. and Goldstein M. : Multivariate Analysis Methods and
Applications, New York, John Wiley and Sons 1984.
7.12 QUESTIONS :
1) Discuss survey method and highlight advantages and disadvantages of
survey.
2) What do you mean by survey method? Explain advantages and
disadvantages of survey method.
munotes.in
Page 60
60 8
QUESTIONNAIRE
Unit Structure
8.0 Objectives
8.1 Introduction and Meaning
8.2 Objectives of Questionnaire
8.3 Advantages of Questionnaire
8.4 Disadvantages of Questionnaire
8.5 Techniques of constructing a Questionnaire
8.6 Summary
8.7 Questions
8.8 References
8.0 OBJECTIVES
1) To make stud ents aware about the tealines , uses and importance of the
Questionnaire method as a tool of data collection.
2) To Tamilaise students to understand Questionnaire method as scientific
method to collect reliable method for collection of data.
8.1 INTRODUCTION AND MEANING
It is defined as “A list of questions given to a human for them to answer.
It secures standardized result that can be tabulated and tested statistically.
(Bogandus
questionnaire refers to a device for securing
answers to questions by using a for m which the respondent fills in himself.
(Goode Half - Methods of social Research) Questionnaire is a set of
predetined questions. Generally it is mailed to the respondents for
collecting data. It is employed when the area of study is wide and the
subjects are widely dispersed. In this method the researcher does not
collect the data by himself. He relies on the information provided by the
respondents.
8.2 OBJECTIVES AND TYPES OF QUESTIONNAIRE
There are two basic objectives of Questionnaire :
1) To collect informat ion from the respondents who are scattered in wide
area.
2) To achieve success in collecting reliable and dependable information. munotes.in
Page 61
Questionnaire
61 Types of Questionnaire :
a) Structured Questionnaire :-
This questionnaire is named before the study is started and it is not
possible to change it offer beginning the study.
b) Non Structured Questionnaire :-
This kind of Questionnaire is used more like a guide. It consists of definite
subject matter areas, the coverage of which is required during the process
of data collection . It is generally used in the technique of interview in
which case it is called an interview schedule.
Questionnaire is also divided on the basis of nature of the questions that it
contains. They are closed, open, pictorial and mixed. Closed questionnaire
usually contains itemized answers to the questions being asked various
alternatives to the real answer are also given. The respondent is only to
select the answer and put it down.
Open Questionnaire is just the reverse of the closed questionnaire. It is
used in the cases where new facts are to be found out. The respondent is
given the liberty to express his views freely.
Pictorial questionnaire is similar to closed types of questionnaire.
Generally it is use for children of small age group on illiterates on person
with lower. I.Q. Along with the questions, pictures showing the meanings
of those questions one given. The respondent is required to give out the
answers on the basis of pictures.
Mixed questionnaire is neither completely closed non open.
It consis t of both the type of questions. Since it is combination of the types
of the questions it is popular in social research.
8.3 ADVANTAGES OF QUESTIONNAIRE :-
Questionnaires are very cost effective when compared to face interviews.
This is especially true for studies involving large sample size and large
geographic areas. Written questionnaire become even more cost effective
as the number of research questionnaire increases.
Questionnaires are easy to analyze. Data entry and tabulation for nearly all
survey s can be easily done with many computer software packages.
Questionnaires are familiar to most people. Nearly everyone has had some
experience completing questionnaires and they generally do not make
people apprehensive.
Questionnaires reduce bias. The res earcher’s own opinion will not
influence the respondent to answer questions in a certain manner. There are
no verbal on visual clues to influences the respondent. munotes.in
Page 62
Quantitative Social
Research
62 Questionnaires are less intrusive than telephone on face -to- face surveys.
When a respondent receives a questionnaire in the mail, he is free to
complete the questionnaire on his own time -table. Unlike other research
methods, the respondent is not interrupted by the research instrument. \
Check your profress :
1) Discuss the meaning of questio nnaire.
2) What are advantages of Questions.
8.4 DISADVANTAGES OF QUESTIONNAIRE :-
One major disadvantage of written questionnaire is the possibility of low
response rates. Low response is the curse of statistical analysis. It can
dramatically lower own confi dence in the results. Response rates very
widely from one questionnaire to another (10% -10%), however, well -
designed studies consistently produce high response rates.
Another disadvantage if questionnaire is the inability to probe responses,
Questionnaires are structured instruments. They allow little flexibility to
the respondent with respect to response format.
By allowing frequent space for comments, the researcher can partially
overcome this disadvantage. Comments are among the most helpful of all
the information on the questionnaire, and they usually provide insightful
information that would have otherwise been lost.
Nearly ninety percent of all communication is visual. Gestures and other
visual cues are not available with written questionnaires. T he la ck of
personal contact will have different effects depending on the type of
information being requested. A questionnaire requesting factual
information will probably not be affected by the lack of personal contact. A
questionnaire probing sensitive issues on attitudes may be severely
affected.
Finally, questionnaires are simply not suited for some people. For
example, a written survey to a group of poorly educated people might not
work because of needing skill problems. People are turned off by written
questionnaires because of misuse.
Check your progress :
What are the disadvanteges of questionare.
8.5 TECHNIQUE OF CONSTRUCTING A QUESTIONNAIRE
In case, the study is to be conducted through questionnaire method, the
questionnaire has to be drawn up in a sc ientific manner. The framer of
questionnaire should keep certain things in view will constructing this
device. In this method the respondent gives his answers from a distance.
The language and the wordings of the questions should be stimulating to
the resp ondents to give replies. The psychology of the respondent should munotes.in
Page 63
Questionnaire
63 be kept in mind and the questionnaire should be framed keeping in view
the factors that are likely to encourage him to give correct answers.
1) Number of questions :-
A questionnaire should be contain a large number of questions. If there are
two many questionnaire, generally respondents loose interest and start
giving irrelevant answers. Thus a questionnaire should neither be too long
no to brief.
2) Questions should be unambiguous, clean and simple :-
Double barreled questions should not be used. One should not include two
or more question in one. (e.g. Does your department have a special
recruitment policy for racial minorities and women). Such a question
typically leads to hesitation and indeci sion on the part of the respondent.
Some wounds are themselves vague and ambiguous. Themes such as
social integration for example, many not well known to the respondents.
The meaning of some wounds may be known only to highly educated
respondents. Slang on colloquial phrases may be known only to one
group, on may have different meanings to different groups. Such
differences can present a real communication problem if the group of
respondents is not homogeneous. After resolving to avoid ambiguous
wordings is appropriate. This vary often depends upon the educational
level of the respondents. Many researchers feel that they should phrase
their questions in the respondents everyday slang so as to maximize
rapport between respondent and researcher. This is perhap s on those
matters for which there is no right or wrong choice. Moreover the
questions should refer to concrete and specific matters like age on sex are
specific but opinion questions are especially difficult. The respondent
often does not have an option because he or she has never thought about
the topic. He or she is concerned about appearing stupid and must be
measured that there is no right or wrong answer.
3) Leading questions :-
Questions should be carefully structured in order to minimize the
probabilit y of biasing the respondents answer by leading him or her and
thus artificially increasing the probability of a particular response. The
researchers task is to avoid leading questions as for as possible or to use
neutral wordings instead.
4) Technical and special words should be clearly explained :-
While using technical jargon the researcher needs to provide an adequate
explanation to all the words so as to enable the respondent to understand it
in a connect way.
5) Personal questions :-
Very personal questions should be avoided . Respondents are generally
unwilling to write down such information. Personal questions should be munotes.in
Page 64
Quantitative Social
Research
64 asked only if completely required.
Besides these considerations certain technical considerations should be
kept in mind like
a) Quality of paper used.
b) Response category format.
c) Mailing facilities etc.
d) Layout of a questionnaire
When technique of questionnaire is used in scientific surveys and when the
sample size is big ; it is always advisable to attach a Covering letter to the
questionnaire. A good covering letter includes the following.
1) A brief introduction of a researcher/researchers and basic information
about the institution involved in the process of research.
2) Statement regarding the purpose of survey undertaken.
3) Enclose a self -addressed en velope for the respondents convenience in
returning the questionnaire.
4) Assume the respondent that the information he gives will be kept
confidential.
5) Promise the respondent that he will bet solicited after he fills up
questionnaire.
6) If the respondent is in terested, promise a copy of the results of the
survey to him.
7) If possible and if required aff er social incentives to the re spondents on
the return of the questionnaire.
8.6 SUMMARY :-
The use of questionnaire depends on devoting the right balance of eff orts
to the planning stage, rather than rushing too early administering the
questionnaire. Therefore the researcher should have a clear plan of action
in mind and costs, production, organization, time limit and permission
should be taken care in the beginn ing while designing of questionnaire, the
characteristics of a good questionnaire should be kept in mind.
8.7 QUESTIONS :-
1) Explain questionnaire, Discuss advantages and disadvantages of
questionnaire?
2) Write a detail notes on questionnaire method.
3) Discuss meani ng of questionnaire. munotes.in
Page 65
Questionnaire
65 4) Analyze objectives of questionnaire.
5) What are the advantages of questionnaire ?
6) Explain disadvantages of questionnaire
7) What are the techniques is conduct questionnaire explain.
8.8 REFERENCES :-
1) Anthony Gliders, Positirsm and sociology , Cambridge, Gower 1987.
2) Baily Kenneth, Methods in social research, The freepren 1978
3) Ker linger F.N., Foundations is behavioral Research, Hilt Rinehart and
Winston Inc 1964.
4) Kumar Ranjit, Research Methodology Ed. 2, Pearson Education, 2006.
munotes.in
Page 66
66 9
SAMPLING TECHNIQUES
Unit Structure
9.0 Objectives
9.1 Introduction
9.2 Objectives of sampling
9.3 Merits of Sampling
9.4 Demerits of Sampling
9.5 Classification of Sampling Method
9.6 Types of Probability Sampling
9.6.1 Random Sampling:
9.6.2 Stratified Sampling
9.6.3 Multistage/Cluster/Area Sampling
9.7 Types of Non -Probability Sampling
9.7.1 Convenience sampling/accidental sampling
9.7.2 Quota sampling:
9.7.3 Purposive or judgment sampling:
9.8 Questions
9.9 Reference and Further Readings
9.0 OBJECTIVES
To know the principal and objective and concept of sampling
To know the advantages and disadvantages of sampling
To know various types of sampling and its application in statistics
9.1 INTRODUCTION:
Sampling is the process of drawing sample from the population. A sample
is a porti on, selected from the universe or population in statistics.
In statistics ‘population” means “all individual things, event or observation
that a particular study wants to cover for e.g. the population of a study
dealing with the views of college students s tudying in various colleges in munotes.in
Page 67
Sampling Techniques
67 the city. The sample is considered to be the representative of the universe.
If the sample has been properly selected and its size is appropriate,
whatever holds good for the sample also holds good for the universe.
9.2 OBJEC TIVES OF SAMPLING:
i. Selecting the sample of adequate size
ii. Collecting the information
iii. Making Inferences about the population
9.3 MERITS OF SAMPLING:
1. A sample survey is time saving and less expensive as compared to
census survey.
2. A sample survey requires smal l administrative organization because;
i. The field of survey is small.
ii. Number of staff needed is small
iii. The volume of information to be collected and processed is small.
3. The result obtained from the sample method is accurate and more
reliable then the census method. In this method the investigation
comes to know about the statistical error.
4. Since the coverage is limited detailed information can be obtained.
5. If the population is very large, hypothetical sampling is the only
method of studying the population characteristic.
9.4 DEMERITS OF SAMPLING:
1. This method is not suitable where high degree of accuracy is required.
2. In the absence of expert investigations, the result obtained from this
method cannot be realied on.
3. This method is not suitable when there is h eterogeneity.
4. If care is not taken in the selection of sample the conclusion drive from
them will be mis -leading.
9.5 CLASSIFICATION OF SAMPLING METHOD:
Sampling method can be classified into two broad categories,
a) Probability sampling : -
In probabil ity, selection of each respondent is known.
b) Non-probability sampling: - munotes.in
Page 68
Quantitative Social
Research
68 In non -probability sampling the probability of selection is not known.
9.6 TYPES OF PROBABILITY SAMPLING:
Hess (1985) in her historical analysis of sampling provides many good
examples of different types of probability which are as follows.
9.6.1 Random Sampling:
The best known form of probability sampling is random sampling. In a
random sampling each person in the universe has an equal probability or
chance of being selected regardless of sim ilarities or differences among
them as long as they are members of same universe.
All that is required to conduct a random sample is to select a person
without showing bias for any personal characteristics. Accuracy of the
random sample depends on the accu racy sample frame. If same person are
listed for more than once, then they will have greater probability of being
selected. If other persons are omitted from the list they will not be selected
at all. In either of the cases the sampling will not be random.
Random sampling is used to obtained a sample i.e. most likely to be
representative of the population. Random sample has a technical meaning
in statistics. It does not mean hap -hazards or unplanned, when items are
not selected by choice but by chance. It i s called random sampling. This
method is also known as ‘chance selection.’
The following methods are used for obtaining a random sampling:
Lottery method.
Table of random numbers.
Arrangement of all number in same order and every 5th, 10th, 100th or
nth unit is selected.
One important property of simple random sample is that the larger the size
of sample the more likely is that its mean will be close to the population.
Merits of Random Sampling:
i. Since the selection of the item in the sampling depends e ntirely upon
chance there is no possibility of personal bias affecting the result.
ii. Compared to judgment a random sample represents the universe in a
better manner.
iii. We can calculate the margin of errors because the sampling error
follows the principle of ch ance.
Demerits of Random Sampling: munotes.in
Page 69
Sampling Techniques
69 i. Simple random sampling requires a complete catalogue universe from
which a sample is drawn. However, it is very difficult to have up -to-
date list of all the items of the population to be sampled.
ii. In a field survey the cas es are selected by random tend to be too
widely dispersed geographically. Therefore, it is costing in terms of
time and cost of collecting data.
iii. The size of the sample requires ensuring satisfied reliable results in
usually larger under stratified sampling then random sampling.
9.6.2 Stratified Sampling:
In this method the population is divided into different groups or classes
called a strata and a sample is drawn from each stratum at random. The
purpose of stratification is to increase t he efficiency of sampling by
dividing a heterogeneous population in such a way that there is great
homogeneity with each strata and marked difference between different
strata.
A stratified sample is controlled so that it reflect exactly some known
characte ristics of the population. In a stratified sample everything is not
left to the chance. For.eg: In a public opinion poll it is important that the
sampling reflects the ratio of population who are Hindus, Muslims,
Christians and others.
Stratified sampling of a group or ranked ordered such as professors
associated professor assistant professors. Stratified sampling consist of
listing all professors together in a homogeneous group, then all professor
and assistant professors after that is done a random sampli ng is drown
within each group the procedure not only avoids the biases but also saves
time and money.
Stratified sampling is not limited to stratification of only one variable. One
can stratify o n two more variable simultaneously.
9.6.3 Multistage/Cluster/Area Sampling:
Cluster sampling is sometimes called as area sampling cluster sampling
samples among clusters. It is mainly concerned with the particular
geographical area or a particular aspect of population blocks.
Under this method the random selection is mad e at primary, intermediate
and final units from a given population. At first the 1st stage unit are
sampled by some suitable methods such as simple of 2nd stage unit is
selected from 1st stage unit. Again by some or different form the method
used from the 1st stage unit. Further stage may be added be added as
required. For.eg: - as we take e.g. of 10,000 students from Bombay
university we take colleges as 1st units, then draw departments at the 2nd
stage and choose students at the 3rd and the final stage.
Merits: munotes.in
Page 70
Quantitative Social
Research
70 i. When the area of inquiring is wide this method is used.
ii. It brings flexibility in sampling which is lacking in other methods.
iii. The obvious advantage of cluster sampling is great saving in time and
money.
Demerits:
a. This method is very complicated and le ss accurate than other method
of sample selection by a single stage process.
b. It is not a single sample but two or more, with a possibility of
sampling error in each.
c. This means that the investigator must be concerned about sample size
and accuracy not once but at every stage.
9.7 TYPES OF NON -PROBABILITY SAMPLING:
Non-probability sampling cannot claim to be representative since the
probability of person to be chosen is not known. This greatly limits the
investigators ability to generalize his/her findin gs beyond the specific
sample studies.
The obvious advantage of non -probability sampling is that it is much less
complicated, much less expensive and may be done on a spur of the
movement basis to take advantage of available response without the
statistic of the probability sample. A non -probability may prove perfectly
adequately if the researcher has no desire to generalize his/her findings
beyond the sample or if the study is nearly a trial run for a larger study.
9.7.1 Convenience sampling/accidental sampling:
In convenience or accidental sampling the investigator chooses the closet
person as respondent, this method is also known as ‘hit’ or ‘miss’ or
‘chunk.’ A ‘chunk’ is a part of the population which is selected by
convenience. The investigator selectes cert ain items from the domain as
per his/her convenience that is the method by which a tourist studies the
country of his visit. He comes across certain people and things have
transaction with them and then try to generalize about the entire
population in his travelogue.
What is lost in sampling accuracy is saved in time and money. If a person
is to submit a report from labor management relation in textile industries,
he is following convenient sampling. It is suitable for making pilot studies.
However, the res ults rarely represent the population. They give biased
unsatisfactory results.
9.7.2 Quota sampling:
It is type of judgment sampling. In a quota sampling, quotas are set
according to some specific characteristic. For.eg: - sex, occupation, munotes.in
Page 71
Sampling Techniques
71 education, age, etc. i. e. so many in each occupation, so many in each age
and so on. Each interviewer is asked to interview a certain number of
people who constitute his quota. Within the quota the selection of sample
items depends on personal judgment. For.eg: - in a radio liste ning survey
the interviewer may be asked survey the interviewer 500 people living in a
certain area and that out of every 100 person interview 60 are to be
housewives, 25 farmers and 15 children within this quota the interviewer
is free to select people.
The cost per person’s interview may be relatively small for quota sample
but there are numerous opportunities for biases which may invalidate the
results. Because of the risk of personal prejudice and bias the quota
sample is not used in public opinion s tudies.
The success of this method depends upon the integrity and professional
competence of investigations. It provides satisfactory results if the
interviewers are carefully trained and if they follow their instruction
closely.
9.7.3 Purposive or judgment samp ling:
In this method investigation has complete freedom in choosing his
sampling according to his wishes and desire. To choose or to leave the
item for the purpose of study depends entirely on the wishes of the
investigation and he chooses items which he thinks are the most
representative of the universe. For.eg: - if a sample of 10 students is to be
selected from the class of 60, the investigation would select 10 students
who in his opinion are representative of the class.
Use of judgment sampling is justi fied where a small number of sampling
units are there in universe or when we want to study some unknown traits
(quality) of population or in solving everyday business problems.
Executive or public officials are often pressed for time. Judgment
sampling is then the only practical method to arrive at solution to the
urgent problems.
The disadvantage of this method is that although this simple, it is not
scientific because the sample units may be biased by the personal
prejudices of the investigation. Since a n element of subjectiveness is
possible. This method cannot be recommended for general use.
The success of this method depends upon the excellence in judgment. If
the individual making the decision is knowledgeable about the population
and has good judgmen t only then the resulting sample may be
representative.
9.8 Questions
1) outline sampling & explain its classification. munotes.in
Page 72
Quantitative Social
Research
72 2) What do you understand by the concept orf sampling. Explain
probability/ non -probability sampling in details.
9.9 REFERENCE AND FURTHER REA DINGS
Best, J., Kahn, J. (2008) Research in Education (10th ed.). Prentice
Hall. Pearson Education
Bryman, A. (1988). Quantity and Quality in Social Research. London :
Routledge
Bryman, A. (2008). Social Research Methods. Oxford University Press
Goode , W., Hatt, P. (1981). Methods in Social Research. McGraw -Hill
Book Company
Matt, H., Weinstein, M., Foard N. (2006) A Short Introduction to
Social Research. New Delhi: Vistaar Publications
Somekh, B., Lewin, C. (ed) (2005). Research Methods in the Soc ial
Sciences. New Delhi: Vistaar
munotes.in
Page 73
73 10A
MEASURES OF CENTRAL TENDENCY
Unit Structure:
10A.0 Objectives
10A.1 Introduction & Meaning
10A.2 Types of Average
10A.3 Summary
10A.4 Check your progress
10A.5 References
10A.6 Questions
10A.0 OBJECTIVES
To acquaint students with s tatistical terms.
To familiarize students with Mean, Median & Mode for presenting
data.
10A.1 INTRODUCTION & MEANING
One of the objectives of the analysis of data is to get one single value
which can describe characteristics of the entire mass of the data, which
can be considered as representative of the entire distribution. A value
satisfying this criterion is a central value or an “average ”
In practice, the word “average” is used with different meanings. For
instance, an average student, average height of boys, average Hindi film,
average actor, average income, etc. In some cases, we use the term
“average” to denote a mediocre type e.g. average student, average
actor, average film, etc. In some other cases by the expression
“average” we mean “typical” or “ usual” e.g. average Indian, average
housewife etc. In statistatical terms the average refers to a value of
obtained by a specific process like average height or average income.
In Statistics, the average is representative or typical value of the data. It
usually lies somewhere near the centre of the group and that is why the
averages are termed as measures of Central Tendency or Central Value.
It depicts the main characteristics of the data. Large volumes of data
cannot be easily understood or remembered. So a single value,
summarizing prominent features of the data is needed.
If two or more sets of data are to be compared, it is not possible to
compare each and every item. So, we require one figure, representing the munotes.in
Page 74
Quantitative Social
Research
74 entire data in condensed form. For examp le, average salaries of
employees of two companies of same type can be compared. Suppose these
are Rs. 2,500 and Rs. 2,150. The employees of the second company can
demand a raise in salary based on these results, or suppose, average marks
at the terminal examination of students of two divisions of F.Y.B.Com.
are 65.2 and 45.8 respectively. Then, some arrangement of special
coaching can be made for students of second division. Thus, averages can
facilitate inter-comparison of different characteristics.
While drawing conclusions, care has to be taken to study the number of
forces affecting the data. For instance, in the previous example of students
of two divisions, the divisions might have been formed according to
marks at H.S.C. examination and the first
division may have students with higher percentage, which explains the
average marks of 65.2 at terminal examination. Another points to be noted
is the same type of measure must be used to compare two or more sets of
data.
Requisites of a Good Average:
1. It should be easy to understand and easy to calculate.
2. It should be based on all observations.
3. It should be capable of further algebraic treatment.
4. It should not be affected by extreme values.
5. It should not be affected much by sampling fluctuations.
10A.2 TYPES OF AVERAGES
The averages can be classified into two groups - mathematical averages
and positional averages.
The mathematical averages are based on all observations and they are
calculated using mathematical formulae. The averages are:
(i) Arithmetic Mean
(ii) Geome tric Mean
(iii) Harmonic Mean
However, we will study only the first two averages.
The Positional averages are based on only some of the observations and
are located at a specific place in the sets. They are also called “measures
of location.” They are:
(i) Median
(ii) Mode munotes.in
Page 75
Measures Of Central Tendency
75 Let us study these measures in detail.
Arithmetic Mean:
The most popular measure of central tendency is Arithmetic mean. It is
the arithmetic mean, which is referred to by a common man as an
“average”.
In simple terms, the mean is computed by dividing sum of all
observations by the number of observations.
For ungrouped data (where frequency distribution is not formed)
If there are n observations in the set and these represent different values
123, , ,..............nXXX X of the v ariate x, then the arithmetic mean, denoted
by X, is calculated as follows. Sumof theObservationsXNumberof theObservations
123 ........nXXX Xn
If we denoted the sum 123 1.........nX X X X as X xXn
Note: We may choose any constant as the value of C.
Daily
Wages in
Rs. (Class -
Interval Number of
Workers
f Class Marks x u fu
50 - 55 10 52.5 0 0
55 - 60 22 57.5 1 22
60 - 65 30 62.5 2 60
65 - 70 20 67.5 3 60
70 - 80 12 75.0 4.5 54
80 - 100 6 90.0 7.5 45
Total 100 241
Now,100, 241.0, 52.5 5N f fu A and C
The formula is fuXA CN munotes.in
Page 76
Quantitative Social
Research
76 241.052.5 510052.5 12.05 64.55 .64.55Rs
So, the average daily wages are Rs. 64.55
Merits of Arithmetic Mean:
(i) It is easy to understand and easy to calculate .
(ii) It is rigidly defined, so that a unique answer is obtained.
(iii) It is based on all the observations, which can be seen from the
formula xXn
(iv) Further mathematical treatment is possible in case of arithmetic
mean. For instance, mean for the combined group can be calculated
knowing means of individual groups.
(v) If number of items and their average are known, the sum of the
values of these items can be directly obtained.
(vi) As sum of the deviations of the values from the arithmetic mean is
zero, it balances the values on either side of it. So, it is better
representative than any other average.
(vii) It is less affected by sampling fluctuations and so it has a sampling
stability.
Demerits of Arithmetic Mean:
(i) As its computation requires all values, if some values are not known, it
can not be calculated.
(ii) It is a value which may not be present in the data. That is, there may
not be even one item whose value coincides with value of the
arithmetic mean.
(iii) Sometimes, it may give absurd results like the average number of
students per class is 50.4.
(iv) It is affected by extreme values, i.e. those, which are either too large or
too small.
e.g. the mean of 50, 75, 65, 57, 48 is 59.
If we consider the last observation as 480 instead of 48, i.e. the
mean of 50, 75, 65, 57 and 480 is 145.5.
(v) In case of open end class intervals, the arithmetic mean can not be
computed, unless some assumption about size of class intervals is
made. munotes.in
Page 77
Measures Of Central Tendency
77 MEDIAN:
Median is an important measure of location . When the raw or ungrouped
data are arranged in ascending or descending order, the middle
observation or the arithmetic mean of two middle observations is the
median . The median can be obtained without any formula as follows.
i) For Ungrouped Data :
If x 1,x2,……x n are n observations, arranged in ord er, then median is
defined as Median 12nth observation if n is an odd number =
arithmetic mean of 2nthe observation and 12nthe observation if n is
even.
Illustration 1:
Find median for the following set of observations 53, 42, 30, 55, 75,
50, 32, 39, 62.
Solution:
First arrange the values in ascending order as 30, 32, 39, 42, 50, 53, 55,
62, 75.
Now, n = no. of observations = 9
So, the middle observation is the fifth observation. Hence, median =
50.
Illustration 2:
Find median for the following data containing ten observations. 93, 32,
47, 55, 78, 65, 95, 100, 86, 70.
Solution:
First arrange the data in descending order as 100, 95, 93, 86, 78, 70, 65,
55, 47, 32. Now as the number o f observations is ten, an even number,
there is no single middle observation. But the pair (78, 70) can be
considered as the middle pair.
So, median = average (arithmetic mean) of the pair 78 707420
Hence , median is 74.
munotes.in
Page 78
Quantitative Social
Research
78
(i) For Grouped Data:
Consider the case of discrete variate.
Median is defined as the value of the variable, for which
cumulativefrequency exceed 2n where N represents the total number
of observations.
Illustration 3:
Find median for the following data representing the ages in years of
children.
Age in Years 3 4 5 6 7 8 9 10 No. of Children 14 20 40 54 40 18 7 7
Solution:
Age
x No. of Children
f Cumulative Frequency
(less than) Cf
3 14 14
4 20 34
5 40 74
6 54 128
7 40 168
8 18 186
9 7 193
10 7 200
Total 200
Here, 200200 10022NNf
By comparing 100, with the cumulative frequencies, we get 128 as the
first cumulative frequency exceeding 100 i.e. 2N. The value of x,
corresp onding to the cumulative frequency 128 is 6, which gives the
median value.
So, the median is 6.
Continuous Variate Case:
Now, consider the case when the variate is continuous expressed with
the help of class intervals.
munotes.in
Page 79
Measures Of Central Tendency
79 Firstly, the median class is located as the one for which the cumulative
frequency exceeds 2N.
The following procedure is followed.
Let 1lower class limit of the median classl
2upper class limit of the median class
f = frequency of the median classcf = cumulative frequency of the premedian classl
Now, median is calculated using the formu la,
21
12Nl l cfMedian lf
Now consider the following example.
Illustration 4:
Calculate the median for the following data:
Monthly Income in Rs. No. of Families 1500 -1700 70
1700 -1900 100
1900 -2100 120
2100 -2300 150
2300 -2500 100
2500 - 2700 60
Solution:
We prepare the table of cumulative frequencies to locate the median
class.
Monthly Income in
Rs. No. of Families Cumulative
Frequency
1500 -1700
1700 -1900
1900 -2100 70
100
120 70
170
290
2100 -2300 150 440
2300 -2500
2500 -2700 100
60 540
600
Total 600
munotes.in
Page 80
Quantitative Social
Research
80 Now, 600,Nf an even number 3002N
By comparing 2N, that is, 300, with the cumulative frequencies, find the
first cumulative frequency exceeding 300. It is 440, so the corresponding
class interval 2100 -2300 is the median class.
Here, 1 liml lowerclass it
2 lim
150290l upperclass it
f frequency
cf cumulative frequencyof the previous
Substituting these values in the formula,
Median 2
112Nl cflf 2300 2100 300 2902100150200 10 20002100 2100150 1502100 13.3333 2113.3333
So, the median income is Rs. 2113.33
Illustration 5:
Find the median for the following data:
Class Interval 5-9 10-14 15-19 20-24 25-29 30-34 35-39
Frequency 8 18 27 21 10 8 7
Solution:
First we take the class intervals exclusive type, by adding 10 90.52
to the upper class limits and subtracting 0.5 from the lower class limits.
So, the new classes with class boundaries are 4.5 -9.5, 9.5 -14.5 and so on.
The following table is prepared to find cumulative frequencies and the
median class.
munotes.in
Page 81
Measures Of Central Tendency
81 New Class Interval Frequency Cumulative Frequency
4.5 - 9.5
9.5 - 14.5
14.5 - 19.5
19.5 - 24.5
24.5 - 29.5
29.5 - 34.5
34.5 - 39.5 8
18
27
21
10
8
7 8
26
53
74
84
92
99
Total 99
Now, N=99 and 9949.522N
After comparing 49.5 with the cumulative requencies, as 53 exceeds
49.5, the median class is 14.5 -19.5. 1 14.5, 2 19.5, 27, 26l l f cf
Using the formula,
Median 21
12Nll c flf
19.5 14.5 49.5 2614.5275 23.5 117.514.5 14.527 2714.5 4.35 18.85
Hence, median is 18.85
Merits of Median:
(i) It is easily understood and the calculations are also simple. In some
cases, it can be obtained by mere inspection.
(ii) It is not affected by extreme values.
(iii) It is a value which exists in the data in many cases .
(iv) For attributes, median can be calculated.
(v) If some extreme values are not known and the total number of
observations is known, median can be obtained.
(vi) When the distribution of the data is not symmetrical, median is an
appropriate average. munotes.in
Page 82
Quantitative Social
Research
82 (vii) Median can be located graphically with the help of ogives.
(viii) The sum of the absolute deviations of the values from the
median is minimum.
Demerits of Median:
(i) It is not based on all observations so it may not be a good
representative of the data in some situations.
(ii) It is affected by sampling fluctuations.
(iii) The median is not capable of further mathematical treatment.
(iv) Its calculation requires prior arrangement of the data in ascending or
descending order.
(v) For continuous variate case, the formula is obtained on the
assumption of uniform distribution of frequencies over the class
intervals. This assumption may not be true.
MODE:
The mode is defined as the value of a variable which occurs most
frequently. It is a value which is repeated maximum number of times or
with highest freque ncy. So, mode is considered as the most typical
average. Graphically, it is the value on x-axis corresponding to the peak of
the frequency curve.
If the data are ungrouped, mode can be obtained from inspection as the
value with the maximum frequency. If we want to calculate the most
common height for a group of students or the most common size of ready
made shirts we have to consider the mode as the average. In marked
surveys, to know consumers’ Preference, mode is considered as the most
suitable average.
For ungrouped data, for small sets mode can be found by inspection. But
for grouped data, mode is calculated with the help of interpolation
formula. If a distribution has two or more values of maximum frequency,
then the distribution is known as bimodal, trimodal or multimodal.
Ungrouped Data:
Mode is determined by observing the given set of values and then locating
the one which is repeated maximum number of times.
Illustration: 7
Following are the marks of 15 students in a certain test. Find the model
marks.
18, 22, 25, 42, 39, 35, 25, 33, 34, 25, 29, 37, 35, 25 and 40 munotes.in
Page 83
Measures Of Central Tendency
83 Solution:
As the marks 25 are repeated maximum number of times, that is 4 times
out of 15 observation. The modal marks are 25.
Now consider,
Grouped Data - Discrete Variate Case
Here mode ca n be obtained as the value of the variable with the maximum
frequency.
Illustration 8:
Find the mode for the following data, representing size of ready made
pants.
Size of pants in cms 60 65 70 75 80 85 90 No. of Pants 11 15 25 40 20 15 10
Solution:
Here the variable x is the size in cms and the frequency f is the number of
pants. As the size 75 cms has the maximum frequency of 40, it is the
modal size.
So, the modal size of pants is 75 cms.
Let us consider,
Grouped Data - Continuous Variate Case
If the distribution has only a single maximum frequency, the mode can be
calculated as follows:
First of all, modal class is located as the class interval with the maximum
frequency.
Let 1 lim modl lowerclass itof the alclass
1
0mod
mod
modof frequencyof the alclassf frequencyof the pre alclassf frequencyof the post alclass
Then mode is given by 21 1 011012ll ffMode lffff
But 1012 102fffffff
munotes.in
Page 84
Quantitative Social
Research
84 So mode can also be calculated as,
21
110 22llffMode lfff
Illustration 9:
Find the mode for the following data:
Income in Rs. 200-400 400-600 600-800 800-1000 1000 -1200 No. of Perso ns 16 34 60 37 13
Solution :
Here the variable is the income in Rs. and the frequency is the no. of
persons. The maximum frequency is 60, so that the modal class is 600-
800, corresponding to the maximum frequency 60.
= lower class limit of the modal class = 600
= upper class limit of the modal class = 800
= frequency of the modal class = 60
= frequency of the pre-modal class = 34
= frequency of the post-modal class = 37
Mode 21 1 9
1
1022llfflfff
800 600 60 34600120 34 37
200 2660049600 106.1225 706.1224 .706.12Rs
So the moda l income is Rs. 706.12
Merits of Mode:
(i) It is easy to understand and easy to calculate.
(ii) By definition, it is the most typical or representative value.
(iii) Mode is not affected by values which are too large or too small.
(iv) It is an appropriate average in qualitati ve data.
(v) It can be obtained graphically from a histogram.
(vi) It can be calculated in open end class intervals or in those cases where
the neighbourhood of point of concentration is known. munotes.in
Page 85
Measures Of Central Tendency
85 Demerits
(i) It is not rigidly defined. A distribution may be bimodal and
multimodal.
(ii) It is not based on all observations.
(iii) It is affected by sampling fluctuations.
(iv) It is not capable of further mathematical treatment.
10A.3 SUMMARY
The definitions of arithmetic, mean, geometric mean, median and mode
are different in the sense tha t, means are mathematical averages and the
other two are positional averages .
The arithmetic mean and geometric mean are based on all observations
while median and mode are not. This fact can be a disadvantage to mean,
because if only one item is not known , then mean can not be obtained.
As calculations of means require all observations, they are affected by
extreme values. But median and mode are not affected by extreme values.
All the measures, except geometric mean, are easy to understand and easy
to cal culate. Median and mode can be found by inspection, in ungrouped
data. But for grouped data, all these measures require some calculations.
In case of open end class intervals, arithmetic mean and geometric mean
can not be calculated, but median and mode ca n be computed for open end
classes as well. The arithmetic mean and geometric mean are capable of
further algebraic treatment, but no such treatment is possible in case of
median and mode. Usually, as arithmetic mean satisfies most of the
requisites of a good average, it is most widely used.
10A.4 CHECK YOUR PROGRESS
1) Explain Mean.
2) Discuss Median.
3) Highlight Mode and its demerits.
10.5 REFERENCES
1) Borwankar P.V. Research Methodology Seth Publisher 1995.
10A.6 QUESTIONS
1) Discuss measures of central tendency
2) Give the merits and demerits of median and mode.
munotes.in
Page 86
86 10B
MEASURES OF DISPERSION
Unit Structure:
10B.0 Objectives
10B.1 Introduction & Meaning
10B.2 Range
10B.3 Quartiles
10B.4 Mean Deviation
10B.5 Standard Deviation
10B.6 Check your progress
10B.7 Referen ces
10B.8 Questions
10B.0 OBJECTIVES
To introduce students with quantitative method of data collection.
To enable students to apply statistical terms in social research.
10B.1 INTRODUCTION AND MEANING
We have studied various measures of central tendency su ch as mean,
median, mode in the previous chapter. But they are not adequate to
describe the distribution. For instance, consider the following sets of
observations:
Set A: 35, 37, 34, 38 and 46 with mean 38
Set B: 10, 90, 45, 12 and 33 with mean 38
Set C: 38, 38, 38, 38, and 38 with mean 38
All the sets have the same mean 38, but if the values in the sets are
observed carefully, it can be seen that in set C, the average 38 completely
represents the distribution; in set A, only one value is represented by th e
average and in set B, average 38 represents none of the values. Also, the
variation of the items is nil in set C and is maximum in set B.
Thus, it is quite clear that in addition to averages, some additional
information about the variation of items is re quired, to know the extent to
which the values vary from one another and from central value. munotes.in
Page 87
Measures of Dispersion
87 A measure of spread of scatter of the data is called a measure of variation
or dispersion.
The measures of dispersion can give us idea about reliability of the
averages. When the dispersion is less, the average is more reliable so that
it is a better estimate of the population average, and if, the dispersion is
more, the average is not a good representative of the data.
The measures of dispersion determine the exten t of variation in the data, by
which, some steps can be taken to control the variability. For instance, in
factories quality control techniques can be applied to control the variation.
The measures of dispersion can be used to compare two or more
distribut ions. The one with less dispersion is more consistent or
homogeneous and the one with more dispersion is less consistent.
The study of dispersion leads to further advanced techniques in analysis
such as Statistical Quality Control, Cost Control, Inventory Control, etc.
Requisites of a Good Measure of Dispersion:
(i) It should be easy to understand and easy to calculate.
(ii) It should be rigidly defined.
(iii) It should be based on all the observations.
(iv) It should be capable of further algebraic treatment.
(v) It should not be affected much by extreme values.
(vi) It should have sampling stability.
There are two types of measures of dispersion.
(a) Absolute Measures giving actual extent of scatter of the data and
(b) Relative Measures expressed as pure numbers, independent of the
unit of measurement.
Corresponding, to each absolute measure of dispersion, a relative measure
can be defined which can be used to compare two or more distributions.
Now, let us study these measures.
10B.2 RANGE
It is defined as the difference between the maximum and minimum
values. It is an absolute measure. Range Maximum Minimum
munotes.in
Page 88
Quantitative Social
Research
88 If we consider the set A,B,C, mentioned earlier.
Range for Set A = 46-34 = 12
Range for Set B = 90 -10 = 80
Range for Set C = 38-38 = 0
So, for the sets A,B,C, even though the means are the same, the ranges
are quite different.
Illustration 1:
The following are the prices in Rs. of different brands of television sets.
Find the range of prices.
Rs. 17850, 16990, 17500, 19850, 16650, 19300
Solution:
Here, Range = Maximum Price - Minimum Price
= 19850 - 6650 = 3200
So, the range of prices is Rs. 3200.
2) Coefficient of Range :
It is a relative measure of dispersion and is defined as, Maximum MinimumCoefficientof RangeMaximum Minimum
Thus, it is a ratio of the d ifference and the sum of maximum and minimum
values. Being a ratio, it is independent of the unit in which the original
variable is measured.
Illustration 2:
Find the coefficient of range for the following data relating to prices of
shares of “ABC” company during a week.
Rs. 25.75, 23.10, 23.50, 29.25, 24.50
Solution:
The maximum price = Rs. 29.25
The minimum price = Rs. 23.10 29.25 23.10 6.1529.25 23.10 52.350.1175Maximum ManimumCoefficinetof RangeMaximum Minimum
munotes.in
Page 89
Measures of Dispersion
89 The range and coefficient of range are used to measure the variation in
prices of commodities, shares, temperatures, rainfall, etc. over a time
period. The range is used to measure variations which are highly sensitive
like gold and silver prices. In day-to-day life, question like “Kow many
answer papers are assessed in a week? Or How many marks are expected
in a particular paper? Or How much profit does a shopkeeper make per
day? Are always answered in the form between, two extreme value.
But statistically it is represented by single number which is interval
between maximum all minimum value called as range.
Merits of Range:
(i) It is easy to understand and easy to compute.
(ii) It is rigidly defined.
(iii) For small sample size, range is a good measure.
(iv) It is affected by extreme values and its value changes from
sample to sample.
10B.3 QUARTILES
Quartile s are not measures of central tendency but they represent three
values dividing the entire distribution of data into four equal parts. As the
calculations are similar to that for median, we consider Quartiles along
with median. The quartiles are called first quartile Q1, second quartile
Q2 and the third quartile Q3. Quartiles occupy specific positions in the
distribution of data. if we arrange all N observations in order, then the
quartiles Q1, Q2 and Q 3 are three points such that they divide the
distribu tion into four equal parts, each consisting of 4Nobservations.
123
4444NNNNQQQ
The figure show four parts, containing 4Nobservations and three values
Q1, Q2 and Q 3.
The number of observations less than Q1 is 4N
The number of observations less than Q2 is 2N
The number of observations less than Q3 is 4N munotes.in
Page 90
Quantitative Social
Research
90
For continuous distribution, using interpolation formula:
(i) Consider the First Quartile Q1
The first quartile class is locate as the one for which cumulative
frequency exceeds 4N. After locating the class interval ,
l1 = lower class limit of the first quartile class,
l2 = upper class limi t of the first quartile class,
f = frequency of the first quartile class,
cf = cumulative frequency of the class preceding the first quartile class,
and and Q 1, is calculated using the formula
21
114Nl l cfQlf
(ii) The Second Quartile Q2coincides with the median.
21
214Nl l cfQlf
(iii) Consider the Third Quartile Q3
The required class interval is obtained by comparing the cumulative
frequency with 34Nand then finding the class for which cumulative
frequency exceeds 34N
l1 = lower class limit of the third quartile class,
l2 = upper class limit of the third quartile class,
f = frequency of the third quartile class,
cf = cumulative frequency of the class preceding the third quartile class.
Q3 is calculated as
21
313
4Nl l cfQlf
Note: There are 25% of the total observation which lie below Q 1. 50%
of the observation are below Q2 and 75% are below Q3. So, there are munotes.in
Page 91
Measures of Dispersion
91 50% observations in between Q1 and Q 2, and so Q1 and Q3 are the limits
within which middle 50% of the observations lie.
Illustration 6:
Find the three quartiles for the following data:
Solution:
We prepare the table for cumulative frequencies.
Daily Wages in
Rs. No. of Workers
Cumulative Frequency
less than
10-15 12 12
15-20 28 40
20-25 36 76
25-30 50 126
30-35 25 151
35-40 18 169
40-45 16 185
45-50 10 195
50-55 5 200
Total 200 = N
For
, consider 2005044N
From the table as 76 is greater than 50, the required class interval is
20-25.
Now, 1220, 25, 36, 40l l f cf
21
11425 20 50 402036
5 10203620 1.3889 21.39Nl l cfQlf
So, the first quartile is Rs. 21.39. Daily Wages in Rs. 10-15 15-20 20-25 25-30 30-35 35-40 40-45 45-50 50-55 No. of
Workers 12 28 36 50 25 18 16 10 5
munotes.in
Page 92
Quantitative Social
Research
92 Now, for Q2 , consider 20010022N
By comparing 100, with the cumulative frequencies, as 126
exceeds 100, the required class is 25 -30.
Now, 1225, 30, 50, 76l l f cf
21
21230 25 100 7625505 24 12025 2550 5027.4Nl l cfQlf
So, the second quartile is Rs. 27.4.
Now, for Q3, consider 3 3 20015044N
By comparing 150, with the cumulative frequencies, as 151 exceeds
150, the required class is 30-35.
Now, 1230, 35, 25, 126l l f cf
21
313
435 30 150 12630255 24 1203025 2530 4.8 34.8Nl l cf
Qlf
So, the third quartile is Rs. 34.8.
Limitation:
(i) It can not be calculated for open end classes.
(ii) It does not take into account the deviations of individuals items from
a measure of central tendency.
(iii) It is not based on all the observations.
munotes.in
Page 93
Measures of Dispersion
93
3) Semi -inter -quartile -range or quartile deviation:
It is defined as follows: 31int2QQSemi er qurtileRange
The semi -inter-quartile range considers only the middle 50% of the
observations and it ignores the first and the last quarter. It is an absolute
measure. The quartile deviation also measures the average amount by
which the two quartiles Q1 3 differ from median. median.
4) Coefficient of quartile deviation:
It is a relative measure and is defined as 31..2QQCoefficientof QD
As, it is a ratio, it is a pure number, so that it can be used to compare two
or more distributions.
Illustration 3:
Find the quartile deviation for the following data of pocket allowances
(Rs.) of 15 student. Also find the coefficient of quartile deviation.
Set A (Rs.): 34, 45, 53, 42, 39, 35, 40, 51, 57, 52, 47, 62, 55, 50, 63
Solution:
Arrange the sets in ascending order of magnitude as
Set A: 34, 35, 39, 40, 42, 45, 47, 50, 51, 52, 53, 55, 57, 62, 63
Here, n = the total no. of observation = 15
114thnQ isobservation = 4th observation
1.40Q Rs
3134thnQ isobservation = 12th observation
3.55Q Rs
Quartile Deviation31 52 407.522QQ munotes.in
Page 94
Quantitative Social
Research
94 Coefficient of Quartile Deviation 31
3155 4055 40QQ
QQ
150.157995
Now consider the quartile deviation for grouped data.
Illustration 4:
Calculate quartile deviation for the following distribution of ages of
800persons. Also find the coefficient of quartile deviation.
Age in Years 20-25 25-30 30-35 35-40 40-45 45-50 50-55 55-60 No. of Persons 50 70 100 180 10 150 70 60
Solution:
As it is a continuous distribution, first prepare the following table to obtain
cumulative frequencies and to locate the required class intervals.
Age in Years No. of Persons Cumulative Frequency
(Less than)
20-25 50 50
25-30 70 120
30-35 100 220
35-40 180 400
40-45 150 550
45-50 120 670
50-55 70 740
55-60 60 800
Total 800
Here, 800Nf
a) For Q1, consider 2004N. As 220 is the first cumulative frequency
greater than 200, the required class for Q1is 30-35.
Now 1 30, 2 35, 100,ll f c f cumulative freq. of previous class =
120.
21
121Nl l cfQlf munotes.in
Page 95
Measures of Dispersion
95 35 30 200 1203010050 80 40030 30100 10034 .yrs
b) For Q3, consider 3600.4NAs 670, is forst cumulative frequency
exceeding 600, the required class interval for
is 45-50.
Now,1245, 50, 120, 550l l f cf
321431(50 45)(600 550)451205 50 25045 45120 12045 2.08 47.08Nl l cfQlfyears
Quartile Deviation 312QQ
47.08 34 13.08226.54
Coefficient of Quartile Deviation = 3131QQQQ
47.08 34 13.0847.08 34 81.080.1613
So, the quartile deviation is 6.54 years and coefficient of quartile
deviation is 0.1613.
Merits of Quartile Deviation:
(i) It is simple to understand and easy to calculate.
(ii) As it is based on middle 50% of the observations, it is not
affected by extreme values. So, it is useful in erratic data.
(iii) It can be calculated for open end classes.
munotes.in
Page 96
Quantitative Social
Research
96 (iv) The quartile deviation can be obtained for qualitative data which can
not be measured but can be ranked.
Limitations:
(i) It is not based on all observations.
(ii) It is not capable of further mathematical treatment.
(iii) It is affected by sampling fluctuations.
(iv) It does not consider the observations in the first and last quarter.
However, it gives a rough idea about the scatter of the data and it is a
better average than range.
10B.4 MEAN DEVIATION
The range or quartile devia tion do not take into account, the deviations
from the central value. The mean deviation considers these differences in
absolute values and averages these differences.
Thus, mean deviation, in which is an absolute measure is defined as the
arithmetic mean of absolute values of deviations of all the observations
taken from the mean, median or mode. Mean deviation from median is
minimum.
For Ungrouped Data
a) M.D. from mean = xxn
M.D. from median = x Mediann
M.D. from mode = modxen
Where n represents total number of observations.
For Grouped Data, N = f
a) M.D. from mean = fx xN
b) M.D. from median = f x MedialN
M.D. from mode = f x ModeN munotes.in
Page 97
Measures of Dispersion
97 2) Coefficient of Mean Deviation:
It is a ratio of the mean deviation and the measure from which the
deviations are considered.
Being a relative measure of dispersion, it is a pure number, independent of
the unit of measurement of the variable. Hence, it can be used to compare
two or more sets of data. It is defined as follows:
a) Coefficient of M.D. from mean =..M D fromMeanMean
b) Coefficient of M.D. from median = ..M D fromMedianMedian
c) Coefficien t of M.D. from mode = ..M D fromModeMode
Illustration 1:
Find the mean deviation from mode and the corresponding coefficient
of mean deviation for the following data:
Income in Rs. 800-1000 1000 -1200 1200 -1400 1400 -1600 1600 -1800 No. of Persons 16 34 60 37 13
Solution:
First calculate mode as follows:
Here the modal class is 1200 -1400 as the corresponding frequency 60 is
the maximum frequency.
Now, 12 1 2 01200, 1400, 60, 37, 34ll f f f
Mode = 21 1 011022llfflfff
1400 1200 60 341200120 34 37200 26 52001200 120049 491200 10.6.12 1306.12
So that modal income is Rs. 1306.12
Now, prepare the following table to calculate modfx e. munotes.in
Page 98
Quantitative Social
Research
98 Income in
Rs. No.of
persons X x Mode modfx e 800-1000 16 900 406.12 6497.92
1000 -1200 34 1100 206.12 7008.08
1200 -1400 60 1300 6.12 367.20
1400 -1600 37 1500 193.88 7173.56
1600 -1800 13 1700 393.88 5120.44
Total 160 26167.20
No, 26167.2, 160f x Mode N
M.D. from mode = mod 26167.2.163.545160xeRsn
Coefficient of M.D. from mode = . . 163.5451306.12M D fromModeMode
0.1252
Merits of Mean Deviation
i) It is rigidly defined.
ii) It is easy to understand.
iii) It is based on all the observations.
iv) Its value is minimum when calculate d from median.
v) It is less affected by extreme values.
vi) As it takes into account deviations from averages it is more
scientific than range or quartile deviation.
Limitations:
i) It requires more calculations for continuous variables.
ii) It ignores the negative signs for deviations and only absolute values
are considered.
10B.5 STANDARD DEVIATION
It is defined as the positive square root of the arithmetic means of the
squares of the deviations of the observations from the arithmetic mean. It
is denoted by
(sigma). It is an absolute measure. munotes.in
Page 99
Measures of Dispersion
99 a) For ungrouped Data
If X 1, X2..........,Xn are n observations then xxn
and 2xxn
The alternative formula
22xxn
b) For Grouped Data
If x 1,x2............ .xn are district values of a variable with frequesncies f 1,
f2.............f n then ,fxx
N where Nf and 2fx xN
The alternative formula is
22fxxN
for continuous variable , x1,x2.........x n are the class marks.
Note : There are two possibilities for value of x. They are (i) x is integer
and (ii) is not an integer. Any one of the two formulae can be used in any
case. But u sually, the first formula is used when x is not an integer, to
simplify the calculation. Now consider some examples.
Illustration 1:
Find standard deviation for the following data:
Class Interval 0-10 10-20 20-30 30-40 40-50
Frequency 11 15 25 12 7
Solution:
The variable is a continuous variable so x represents the class marks of
the class intervals i.e. x values are 5, 15, 25, 35 and 45.
Prepare the following table for the product term fx, fx2 to obtain mean
and S.D. munotes.in
Page 100
Quantitative Social
Research
100 Class
Interval Frequency Class -
mark fx fx2
0-10 11 5 55 275
10-20 15 15 225 3375
20-30 25 25 625 15625
30-40 12 35 420 14700
40-50 7 45 315 14175
Total 70 1640 48150
70Nf 1640fx
164023.428670fxxN
As it is not an integer, we use the following formula for standard
deviation
.
22fxxN
Now, 248150, 23.4286, 70fx x N
Substituting these values, in the formula 22fxxN 24815023.428670
=687.8571 548.8993 138.9578
= 11.7880.
So, the standard deviation is 11.788.
Illustration 2:
Find standard deviation for the distribution of weights of 90 children.
Weight in kgs. 20-25 25-30 30-35 35-40 40-45
No. of Children 11 15 24 26 14
munotes.in
Page 101
Measures of Dispersion
101 Solution:
We prepare the following table to calculate the product terms fx And
fx2 .
Weight in
kgs No. of
Children x
fx fx2
20-25 11 22.5 247.5 5568.75
25-30 15 27.5 412.5 11343.75
30-35 2 32.5 780.0 25350.00
35-40 26 37.5 975.0 36562.50
40-45 14 42.5 595.0 25287.50
Total 90 104112.50
3010fx and 90N, 2104112.5fx
301033.444490fxxN
The standard deviation is given by
22fxxN 2104122.533.444490 1156.8055 1118.5278 32.2777 6.1869
Hence, the standard deviation is 6.1869.
It can be observed that if the class marks are expressed as fractions or if
the class intervals are more, the calculations become lengthy and tedious.
Merits and demerits of standard Deviation
Merits of standard Deviation.
1) It is rigidly defined.
2) It is based on all the observations.
3) It is not affected much by sampling fluctuations.
4) It is amicable to further mathematical treatment. munotes.in
Page 102
Quantitative Social
Research
102 Demerits:
1) It is not easy to understand and easy to calculate
2) As it consider the sum of the squares of deviations of items from the
mean. The items away from mean gets more weight age than those
near the mean. Thus, standard deviation gives more weight age to
extreme value.
10B.6 CHECK YOUR PROGRESS
1) What do you mean by Range?
2) What is Mean Deviation?
3) Explain Quartile deviation.
10B.7 REFERENCES
1) Borwankar P.V. Research -Methodology Seth Publisher 1995.
10B.8 QUESTION
1) What is standard deviation? What are it merits and demerits?
2) What is mean deviation? Discuss its as merits and demerits.
munotes.in
Page 103
103 11
CORRELATION
Unit Structure
11.0 Objectives
11.1 Meaning of Correlation
11.2 Correlation Types
11.3 Coefficient of Correlation
11.4 Limitations of Correlation
11.5 Statistical Correlation Analysis's Usefulness in Social Science
11.6 Summary
11.7 Questions
11.8 References
11.0 OBJECTIVES
To lea rn the meaning and Correlation
To learn about different uses of Correlation
11.1 INTRODUCTION
The use of statistics and statistical tools in social research has been since a
long time, especially with the use of computers in social science research.
Scien tists, researchers have been using various software’s, tools to make
the analysis, documentation, writing, referencing process quicker. In this
chapter we are going to learn about one such topic called ‘Correlation’.
Correlation is not just used in social science research but it is used in
several disciplines starting from Finance, stock markets analysis, to
Economics, natural science etc. In this chapter, we will be looking into
how this topic is relevant and useful in social science and research.
11.2 ME ANING OF CORRELATION
The Cambridge dictionary defines Correlation as a connection between
two or more things, especially when one of them causes or influences the
other. For example – Smoking can cause health related issues. Hence,
there is a correlation between Smoking and health. munotes.in
Page 104
Quantitative Social
Research
104 According to Prof. King, Correlation suggests that there are some random
linkages between two series or groups of data.Cor relation can indicate
whether a change in one variable will result in a change in the other or not.
The degree associationbetween the two sets of characters or variables can
be stated statistically and this is known as the correlation, coefficient.
The stu dy of correlation has many applications in daily life. The French
astronomer Bravis was the first to advance the fundamental ideas of the
science of correlation analysis.Nevertheless, he was also the first to
advance linear correlation theory. Karl Pearson , a statistician, developed
the mathematical formula for computing the coefficient of correlation in
the year 1896. Galton and Karl Pearson used the coefficient of correlation
to examine a variety of biological and genetics -related issues. According
to Pro fessor Neiswanger, who explained the significance of correlation in
the field of economics, correlation analysis contributes to the
understanding of economic behaviour, which helps in locating the
critically important variable. It also reveals how connecti ons and suggest
to him the paths through which stabilising forces may become effective.
Regression and Correlation
Regression and correlation are two distinct yet complementary
approaches. Roughly speaking, correlation is used to assess the strength of
a relationship while regression is used for prediction (which does not
extend beyond the data utilised in the research).
Both correlation and regression analysis focus on how different variables
relate to one another. A measure of the linear link between t wo variables is
the correlation coefficient. The correlation coefficient always has a value
between -1 and +1. A correlation value of 1 denotes perfect linear positive
correlation between two variables, a correlation coefficient of 1 denotes
perfect linear negative correlation between two variables, and a correlation
coefficient of 0 denotes no linear link at all between the two variables. The
sample correlation coefficient for simple linear regression is the square
root of the coefficient of determination, and its value is identical to the
sign of b1, the coefficient of determination.There are instances where the
x variable has a random covariate to the y variable rather than being fixed
or readily selected by the experimenter. Here covariate means Here
covariate means an independent variable that can influence the outcome of
a given statistical trial but which is not a direct one.
Analysis methods like as regression and correlation cannot be used to
demonstrate cause -and-effect relationships. They can onl y show if or how
closely different variables are related to one another. Only the strength of
the linear link (straight line) between two variables is measured by the
correlation coefficient. Any findings on a cause -and-effect link must be
supported by the analyst's judgement. (11)
munotes.in
Page 105
Correlation
105 11.2 CORRELATION TYPES
There are three different types of correlations:
Correlations that are positive, zero, and negative:
(A) POSITIVE CORRELATION:
Positive correlation is a term which is used to describe a relationship
where tw o variables' values move simultaneously and in the same
direction.Perfectly positive or slightly positive correlations of are both
possible in the positive correlation.
(i) Perfect Positive Correlation: This relationship exists when both
variables rise and de crease in the same proportion.
(ii) Moderately Positive Correlation: In this situation, two variables have a
positive correlation, but the changes are not proportional. The coefficient's
value ranges from 1 to 0.
B) NEGATIVE CORRELATION
Negative correlatio n is used to describe a relationship where one variable
increases (or declines) while the other lowers (or increases).
For example - Size and the quantity of fruits or plants, for example, effects
the supply/ shortage adverselyin market.
This adverse relat ionship may also take one of two forms like:
(i) Perfect Negative Correlation: This type of association is incredibly
uncommon in biological contexts, such as when a rise in temperature
causes a drop or fall in the cell's lipid content.
(ii) Moderately Neg ative Correlation: In this relationship, the variables are
negatively connected, but not very completely. For example, a longer
post-harvesting interval reduces seed viability. The coefficient value in
this case is also between 0 and -1.
(C) ZERO CORRELATI ON
The two values of the variables are said to have zero correlation when
there is no correlation between them, i.e., no consistency in the value of
the observation.
11.3 COEFFICIENT OF CORRELATION
The Coefficient of Correlation is a numerical term that descr ibes the
degree of relationship between two variables when there is any direct
interaction between them. The degree of closeness of the linear
relationship between the two variables is expressed quantitatively by this
metric. munotes.in
Page 106
Quantitative Social
Research
106 The correlation coefficient, often known as Karl Pearson's Coefficient of
Correlation and denoted by the letter "r," and is calculated as follows:
How to determine the value of "r":
(A) The variables x and y form two series
(b) The means of the two series, x and y, are calculated.
(c) Each observation's deviation is determined using the variables dx and
dy.
(d) The squared variances are noted.
(e) Multiplying the deviations of the two variables.
(f) The total data are added together using the method to determine the
value of "r."
Correlation coefficient properties include:
1. The correlation coefficient ranges from -1 to +1, or -1 r +1.
2. If r is greater than 1, the correlation is perfect and positive; otherwise, it
is somewhat positive.
3. The connection is complete and negative if r = - 1, and substantially
negative if it is higher than - 1.
4. There is no connection between the variables if r is equal to 0.
5. Change and scale of origin have no impact on the coefficient of
correlation.
Check Your Progress
1. What is positive correla tion
2. Discuss Zero Correlation
munotes.in
Page 107
Correlation
107
Scatter Diagram
An illustration of a correlation is very much helpful. To make this create a
scattergram (also known as a scatterplot, scatter graph, scatter chart, or
scatter diagram).The links or creates affiliations between two numerical
variables (or co -variables) which are graphically depicted as points (or
dots) for each pair of score in a scattergram.The degree and direction of
the correlation between the co -variables are shown on a scattergraph.
It doesn't matte r which variable is plotted on the x -axis and which is
plotted on the y -axis when creating a scattergram.Since paired scores are
always involved in correlations, the values of the two variables combined
will be utilised to create the diagram. Thereafter,Ch oose which variable
belongs on each axis, then draw a cross where the two values meet.
It should be noted that the coefficient of correlation is one of the statistical
measurements that is both utilised and abused the most. It is misused as
sometimes peop le fail to realise that correlation measures are just the
strength of a linear relationship, even in the absence of causality. In other
words, a cause -and-effect link is not always implied.
When two variables are correlated, they are related quantitatively and can
be quantified on either continuous or ordinal scales. Although correlation
implies a link between two variables, it does not imply causality. The
correlation coefficient can be used to determine how strong a correlation
is.
In order to determine t he population correlation coefficient for a given
sample of data, the correlation coefficient which is statistic is calculated.
Correlation coefficients typically range from -1 to +1. High values of one munotes.in
Page 108
Quantitative Social
Research
108 variable are linked to high values of the other, henc e a positive value
denotes a positive correlation between variables, whilst a negative value
implies a negative association between variables (i.e., high values of one
variable are associated with low values of the other). A coefficient of 1
denotes a perf ect negative relationship between the variables, while a
coefficient of 1 denotes a perfect positive relationship. If the correlation
coefficient is 0, the variables are not connected.
If the sample statistic is unlikely to have been taken from a populatio n
with a genuine rho of 0, the null hypothesis that the population correlation
coefficient rho is 0 is rejected when conducting hypothesis testing. The
null hypothesis won't be disproved if the correlation coefficient has a
value of 0. The likelihood of re jecting the null hypothesis rises as the
sample size increases as the coefficient deviates from 0.
Correlation coefficients can be measured using a variety of methods. The
two most well -known statistics are Spearman's rank correlation and
Pearson's product -moment correlation, examples of nonparametric
statistics.The linear relationship between variables is quantified by the
Pearson product -moment correlation coefficient (r) in terms of the
variables' actual raw values. When using the Pearson correlation
coefficient, a normal distribution and linearity are both taken for granted.
The covariance of two variables X and Y divided by the sum of their
respective standard deviations is known as the Pearson correlation
coefficient:
One outlier point has the potentia l to have a significant impact on the
correlation coefficient's value. For purposes of interpretation, r2 denotes
the percentage of a variable's variance that is "explained" by another
variable.
For ordinal variables, or any data that can be ranked, the Sp earman rank
correlation coefficient (rs) is utilised, which necessitates less assumptions
about the distributions of the variables of interest. It is a measure of
correlation for which there may be a nonlinear relationship because it
assesses the strength of the association between the ranks of the data.
The Pearson correlation coefficient and the Spearman rank correlation
both have the same mathematical formula. The quantity of links between
data points has an impact on the rank correlation coefficient. Th e
Spearman coefficient can be stated more succinctly as follows if there are
no ties in the rankings. Where it represents the rank discrepancy between
xi and yi. The Spearman coefficient is unreliable if more than half of the
rankings are tied.
For example - An investigation of the consequences of mercury exposure
at a thermometer manufacturer is one example of how correlation
coefficients are used. The research discovered a strong relationship (r =
0.92) between mercury levels in the air and urine, blood, and hair.
munotes.in
Page 109
Correlation
109 Coefficient and Correlation Significance
It is impossible to overstate the value of correlation in social science
research. Even though it may appear simple, establishing links and
associations between variables has several benefits for the soc ial science
researcher. Below, are few of the importance and significance are briefly
describedin social science research on correlation.One of the most used
methods is correlation matrices, which was often used by Pearson whether
exploratory or explanator y, for examining the concept validity of data in
factor analysis.This approach is also used to find factor solutions and is
confirmatory (Holgado -Tello P. et al 2011).
Regression uses correlation as a starting point to predict the values of the
dependent v ariablesbased on the established link between the independent
variablesas well as the reliant variable too.
The development and evaluation of theoretical models can benefit greatly
from correlational research. The nature of bivariate relations may then be
established, and theoretical models can be created using this knowledge.
Here, the goal is rather than just reporting the bivariate (two variants)
correlations, to describe their nature.
In light of this, techniques like factor analysis, path analysis, and structural
equationModeling may be utilised (Duncan, 1966).
Correlational research has played and will play a significant role in
exploring the nature of the relationships among a collection using
quantitative researchand variables. Unrelated variables ca n be partially
removed from future analysis,enabling the researcher to take relevant
issues more seriously.
Researchers can study numerous factors at once thanks to more advanced
multivariate extensions (Stockwell, 2010). Correlational research can be
performed to look at the relationships between the key variables once
descriptive research has helped to identify them.For instance, researchers
might be curious to know which variables are mosthighly correlated with a
specific result, like student achievement . It may then result inexperimental
studies where the causal relationships between those important variables
canbe investigated under more regulated circumstances even one
independent variable in this casecan be altered by the researcher (e.g.,
instruction method), with other associateda method of controlling the
variables (e.g., grade, level of school funding). This results in a
determination of th e independent variable's impact.
11.4 LIMITATIONS OF CORRELATION
Correlation can be perceived incorrectly, mu ch like other statistical
analysis features. Even if it may seem as though there is a high correlation
between two variables, data from small sample numbers may not be
accurate. In contrast, a small sample size could produce uncorrelated
results even if th e two variables are in fact connected. munotes.in
Page 110
Quantitative Social
Research
110 When an outlier is present, correlation is frequently distorted. Correlation
does not explicitly demonstrate how a specific occurrence or event can
affect the correlation coefficient; it merely illustrates how one var iable is
related to another.
If there is a nonlinear relationship between two variables, correlation may
also be misconstrued. Finding two variables that are correlated either
positively or negatively is much simpler. A more complex link can still be
conne cted with two variables, though.
11.5 STATISTICAL CORRELATION ANALYSIS'S
USEFULNESS IN SOCIAL SCIENCE
These kinds of statistical analyses are helpful because they can illuminate
how experiences and social traits influence what occurs in a person's life
and how various trends or patterns in society, such as unemployment and
crime, might be connected. With the help of correlation analysis, we may
determine with certainty whether or not there is a connection between two
patterns or variables, which enables us to estimate the likelihood of a
result in the population under study.
The amount of education and the divorce rate have a significant negative
link, according to a recent study on marriage and education. According to
data from the National Survey of Family Growth, women's divorce rates
for first marriages decline as their level of education rises.
Although there is a substantial association between education and divorce
rates, it's crucial to remember that correlation does not imply causation,
therefore the decline in divorce among women may not necessarily be
caused by this correlation but caused by the amount of education received.
(Crossman, 2020).
Steps to use Correlation in Excel
Step 1: Enter your data into an Excel worksheet. Two columns make for
the ideal layout. Your x values should go in column A, and your y values
should go in column B.
Step 2: Select "Data Analysis" from the "Data" menu.
The next step is to select "Correlation" and then "OK."
Step 4: Fill out the Input field with the position of your x -y variables.
Variety box. Alternatively, you can use your cursor to identify the region
where your variables are.
Step 5: To tell Excel how your data is organised, click either the "rows" or
"columns" option. You'll typically click "columns" becaus e that's how
Excel typically arranges data.
Step 6: If there are column headings, step 6 is to verify the "Labels in first
row" box. munotes.in
Page 111
Correlation
111 Step 7: choose a location on the worksheet for your output by clicking the
"Output Range" text box. (9).
Example 1: Calcu late the correlation between the two characteristics of
five different plants.
Given that the two characteristics, such as the plant's height and the
number of leaves, are positively associated and that the value of r = 0.986
is as close to 1 as possible , it may be inferred that the relationship is on the
verge of being a perfect positive relationship.
Figure 2:
On the germination of Phaseolus seedlings, the pesticide "Nuvan" is
tested. The correlation coefficient should be known.
munotes.in
Page 112
Quantitative Social
Research
112 To compute "r," the i nformation is set up in the following table:
The correlation coefficient between the two variables, i.e., pesticide
concentration and germination %, is 0.9677, which indicates that they are
negatively associated, though not exactly so.
Check Your Progres s
1. List out the steps of Correlation in Excel.
2. Discuss some limitations of Correlation
11.6 SUMMARY
In this chapter we saw the meaning of Correlation i.e. According to Prof.
King, Correlation suggests that there are some random linkages between
two s eries or groups of data.The relationship known as correlation can
indicate whether a change in one variable will result in a change in the
other or not. The degree of this association, known as the
correlation, coefficient, between the two sets of characte rs or variables can
be stated statistically.The study of correlation has many applications in
daily life. The French astronomer Bravis was the first to advance the
fundamental ideas of the science of correlation analysis; nevertheless, he
was also the firs t to advance linear correlation theory. Karl Pearson, a
statistician, developed the mathematical formula for computing the
coefficient of correlation in 1896. Galton and Karl Pearson used the
coefficient of correlation to examine a variety of biological an d genetics -
related issues. The chapter also discusses about Regression and
Correlation, Coefficient and Correlation. The Chapter also discusses the
importance of Correlation in Social Sciences.
munotes.in
Page 113
Correlation
113 11.7 QUESTIONS
1. Discuss the meaning of Correlation
2. Explain Correlation and Coefficient
3. Discuss Correlation and Regression
4. Explain Correlation and different types.
11.8 REFERENCES:
1. Bryman, A. (1988). Quantity and Quality in Social Research.
London:Routledge
2. Bryman, A. (2008). Social Research Methods . Oxford UniversityPress
3. Matt, H., Weinstein, M., Foard N. (2006) A Short Introduction to
Social Research. New Delhi: VistaarPublications
4. Goode, W., Hatt, P. (1981). Methods in Social Research. McGraw -Hill
BookCompany
5. https://www.investopedia.com/terms/c/correlation.asp
6. Crossman, Ashley. (2020, August 26). Correlation Analysis in
Research. Retrieved from https://www. thoughtco.com/what -is-
correlation -analysis -3026696
7. https://www.simplypsychology.org/correlation.html
8. Samuel, M., & Okey, L. E. (2015). The relevance and significance of
correlation in social science research. International Journal of
Sociology and Anthropology Research , 1(3), 22 -28.
9. https://www.statisticshowto.com/probability -and-statistics/correlatio n-
analysis/
10. A. G. Asuero, A. Sayago& A. G. González (2006) The Correlation
Coefficient: An Overview, Critical Reviews in Analytical
Chemistry, 36:1, 41-59, DOI: 10.1080/10408340500526766
11. https://www.britannica.com/science/statistics/Residual -
analysis#ref367510
12. Wells, George "Correlation Coefficient ." Encyclopedia of Public
Health . . Retrieved June 21, 2022 fr om
Encyclopedia.com: https://www.encyclopedia.com/education/encyclop
edias -almanacs -transcripts -and-maps/correlation -coefficient
munotes.in
Page 114
114 12
INTRODUCTION TO SPSS
Unit Structure
12.0 Objectives
12.1 Introduction
12.2 Understanding SPSS
12.3 Characteristics of SPSS
12.4 Functions of SPSS
12.5 Program in Statistics
12.6 Features of SPSS
12.7 SPSS Statistical Methods
12.8 The benefits of using SPSS
12.9 Uses of SPSS
12.10 Beginning with SPSS
12.11 Limitations of SPSS
12.12 Summary
12.13 Questions
12.14 References
12.0 OBJECTIVES
To learn about the SPSS Software its uses, benefits.
To understand its application.
12.1 INTRODUCTION
The computer is the most recent addition to the research process. A
computer is a necessa ry instrument for research, let it be used for
academic or commercial purposes. Computers are now used in almost all
fields of science, from genetic engineering to astrophysics research. It has
paved the way for the World Wide Web, a multinational informat ion
platform. Researchers can perform large -scale study with the help of
computers.
Since the introduction, computers have always aided in the solution of
issues encountered by human beings. Computers have shrunk in size from
the size of a room to that wh ich can fit in the palm of a human hand. The
computer or a machine today does computations automatically. It
performs a wide range of tasks with incredible speed and efficiency. munotes.in
Page 115
Introduction to SPSS
115 People nowadays utilise computers in nearly every aspect of their lives.
Compu ters play a critical part in all scientific endeavours. Different tools
and software are helping the research process to simplify in the present
times. Various software programmes are now helping such as data
gathering, analysis, and so on. One such Stat istical software is that of
SPSS – Statistical Package for Social Sciences.
In this chapter, we will try to learn about SPSS a Statistical package which
is used to analyse data. You can expect a basic introduction to the
software, its uses, benefits, limi tations. You also learn about some steps
with pictorial images as to how the software actually works. This chapter,
is included in your syllabus as this software SPSS is widely used in
research in recent times. One can even earn a livelihood by learning su ch
software’s like SPSS, R (name of another Statistical software) etc. Several
research firms hire individuals who are excelling in these software’s. In
future, with the introduction of this chapter, you can read more and try out
practically and become an expert if you are interested and even build
careers along these lines.
12.2 UNDERSTANDING SPSS
SPSS was initially released in 1968 and stands for "Statistical Package for
the Social Sciences." Since its acquisition by IBM in 2009, SPSS has been
renamed I BM SPSS Statistics, however most users still refer to it as
"SPSS." This software is mainly used for analyzing quantitative data.
SPSS, is a powerful and comprehensive data analysis tool/ software, has a
plethora of features meant to make the execution of a wide range of
statistical studies easier. It was created for data analysis in the social
sciences as SPSS stands for Statistical Package for Social Science. It is
highly suited to evaluating data from surveys and databases. SPSS is a
groundbreaking piece of software mostly used by researchers that allows
them to handle vital data in easy and quicker ways. Working with data is a
difficult and time -consuming operation, but with the aid of specific
strategies, this programme can simply handle and operate dat a. Different
methods are used to examine, and create a distinctive pattern between
various data variables. Furthermore, the output may be retrieved using a
graphical representation, allowing the user to comprehend the result
quickly.
As seen earlier, SPSS is social science analytical software. It is one of the
best programs for statistical data analysis and computing. It is widely
employed in other fields like as mathematics, health sciences, and even
marketing. It aids in providing ad hoc analysis, selecti ng and performing
analyses, hypothesis testing, data management, and report creation. It also
provides numerous data analysis methods.
SPSS is an analytical software tool for Windows. It may be used for data
entry, analysis, and the development of tables a nd graphs. SPSS is capable
of handling massive volumes of data at the same time. SPSS's objective is munotes.in
Page 116
Quantitative Social
Research
116 to convert raw data into useful information. SPSS provides a variety of
data management capabilities, such as data recording features, a macros
programmer on the visual basic editor, and complicated data sets for
completing aggregations.
SPSS is a statistical analysis tool that is frequently used in the field of
social science, such as market research, surveys, competitor analysis, and
others.
It is a fast a nd adaptable statistical analysis and data management tool. It is
a popular statistical tool that can easily execute very complicated data
manipulation and analysis. It is intended for both engaged and passive
users.
It analyses data for descriptive statis tics, numerical result forecasts, and
group identification. This program also includes data processing, charting,
and direct marketing functions for efficient data management.
What SPSS can do?
Let's look at what SPSS can achieve now that we have a fundame ntal
understanding of how it works. SPSS is ideal for following a normal
project workflow.
Opening data files, either in SPSS's native format or in a variety of
different formats;
Data editing includes sums and means computations over columns and
rows of d ata. SPSS also includes excellent tools for more sophisticated
procedures.
Generating tables and graphs with frequency counts or summary
statistics for (groups of) instances and variables
ANOVA, regression, and factor analysis are examples of inferential
statistics.
Data and output can be saved in a number of file formats.
12.3 CHARACTERISTICS OF SPSS
SPSS is a program that allows you to modify and analyze many types of
data. These data can originate from a variety of places, including scientific
studies, c ustomer databases, Google Analytics, or even from a website's
server log files. The uniqueness about SPSS is also that it can open any
file type that is typically used for structured data, such as MS Excel or
OpenOffice spreadsheets. (.txt or.csv) simple t ext files, relational
databases (SQL); SAS and Stata.
12.4 FUNCTIONS OF SPSS
SPSS's Primary Functions. SPSS has four applications to help researchers
with their sophisticated data analysis requirements like - munotes.in
Page 117
Introduction to SPSS
117 Program on Statistics - The Statistics module in SPSS offers a variety
of fundamental statistical operations, including frequencies, cross -
tabulation, and bivariate statistics, to name a few.
Modeling Software - Researchers may use the Modeler software in
SPSS to create and evaluate prediction model s using advanced
statistical processes.
Program for Text Analytics in Surveys - The Text Analytics for
Surveys tool from SPSS assists survey administrators in gaining
valuable insights from open -ended survey responses.
Designer of Visualization - With SPS S's Visualization Designer
application, researchers may easily build a range of graphics from their
survey data, such as density charts and radial boxplots.
Frequencies, cross -tabulation, and descriptive ratio statistics are
examples of descriptive statis tics.
Prediction techniques such as cluster analysis and factor analysis are
used to identify groupings.
Data Transformation: This method is used to change the data's format.
It unifies the same type of data in one location after altering the data
type, making it easier to handle. You may put any type of data into
SPSS, and it will adapt its structure according to the system's
specifications. This implies that even if you switch operating systems,
SPSS will still be able to deal with previous data.
Linear regression is a type of numerical result prediction.
Regression Analysis is a technique for determining the relationship
between dependent and interdependent variables in a data collection. It
also shows how the dependent data might be affected by a ch ange in
the value of an interdependent variable. The fundamental goal of
regression analysis is to figure out what kind of relationship exists
between various variables.
ANOVA (Analysis of Variance) is a statistical method for comparing
events, groups, or processes and determining their differences. It can
assist you in determining which strategy is best for completing a task.
The feasibility and efficacy of a procedure may be determined by
looking at the results.
MANOVA (Multivariate analysis of variance ): This approach
compares data from random variables with unknown values. The munotes.in
Page 118
Quantitative Social
Research
118 MANOVA method may also be used to investigate different sorts of
populations and the factors that influence their decisions.
T-tests: This approach is used to determine the diff erence between two
sample types, and researchers use it to determine the differences in the
interests of two groups. This test can also determine if the output is
useless or beneficial.
12.5 PROGRAM IN STATISTICS:
The SPSS statistics application provides a wide range of fundamental
statistical features, including frequencies, cross tabulation, and bivariate
statistics, among others.
Program for modelers - Using modern statistical processes, researchers
may create and validate prediction models.
Program of T ext analytics for Surveys - It provides reliable feedback
analysis. It results in a vision for the real plan
Visualization Designer - Researchers discovered this visual designer
data and used it to generate a broad range of graphics such as density
charts a nd radial box plots.
12.6 FEATURES OF SPSS:
• Data from every Survey Device may be readily exported to SPSS for
thorough and detailed analysis.
• Data in SPSS is saved in SAV format. The majority of this information
comes from surveys. This simplifies the process of processing,
analyzing, and pulling data.
• SPSS has simple access to data with many variable kinds. This
variable data is simple to comprehend. SPSS makes it easy for
researchers to put up models because the majority of the procedure is
automat ed.
• Once the data is in SPSS, the magic begins. There is no limit to what
we can do with this data
• SPSS also includes a unique method for obtaining specific data from
large data sets. SPSS features include trend analysis, assumptions, and
prediction m odels.
• SPSS is simple to learn, use, and apply.
• It aids in the acquisition of a data management system and editing
tools.
• SPSS provides extensive statistical tools for examining the actual
outcome. munotes.in
Page 119
Introduction to SPSS
119 • SPSS assists us in improving the clarity of our de sign, graphing,
reporting, and presentation features.
12.7 SPSS Statistical Methods:
SPSS supports a variety of statistical procedures, including the following:
• Prediction for a range of data for group identification, including
approaches such as cluster analysis, factor analysis, and so on.
• Descriptive statistics, especially SPSS techniques, are important for
frequencies, cross tabulation, and descriptive ratio statistics.
• Bivariate statistics, which include procedures such as analysis of
variance (A NOVA), means, correlation, and nonparametric tests,
among others.
• Prediction of numerical outcomes, such as linear regression.
It is a self -descriptive utility that automatically assumes you want to open
an existing file and displays a dialogue box askin g which file you wish to
open. SPSS's methodology makes navigating the User experience
relatively simple.
Aside from statistical data analysis, the SPSS program also has data
management tools, such as the ability to choose data, produce derived
data, and r eshape files, among other things. Data documentation is another
feature. Along with the data file, this feature keeps a metadata dictionary.
Check Your Progress
1. Discuss Data management tool of SPSS.
2. SPSS is most often used in which kind of research m ethodology.
12.8 The Benefits of Using SPSS
There are several benefits of using SPSS some of them are discussed
below -
Data files from other applications may be imported and exported
using the statistical analysis tool. Some of its data processing techn iques
are very useful, such as its capacity to combine files, regardless of whether
they include the same subjects and different variables or separate subjects
with the same variables.
Users are not obligated to work with syntax in SPSS, despite the fact
that syntax files can be stored and edited as needed. When syntax files
are saved, it greatly aids documentation and also provides insight into
how new variables were computed and missing values were handled.
It provides accurate and timely responses.
It's interactive and includes informative tables and graphs. munotes.in
Page 120
Quantitative Social
Research
120 Many individuals can use it because it supports a wide range of
languages.
It provides good data management
It is not difficult to get started with the program.
Both quantitative and qualitative data might be used.
With SPSS, the odds of making a mistake are slim.
One of the simplest statistical methods for data analysis
Users of SPSS can choose the graph type that best fits their data
distribution needs.
12.9 USES OF SPSS
SPSS use is not just restri cted to that of social science research but it has
wider usage. SPSS statistics is a widely used statistical analysis tool in the
corporate sector. Users may manage and analyze data and show it in
visually appealing graphical formats because of its great f eatures and
robustness. It has a graphical user interface and a command -line interface,
making the program more user -friendly.SPSS simplifies the processing of
complicated data. Working with such data is not straightforward, and it is
also a time -consuming procedure.
Let's look at four of the most common sectors where SPSS has been used
to a large extent -
Market Analysis
Businesses desire actionable information to help them make difficult and
effective business choices. Businesses create massive amounts o f data, and
manually scanning them is not the best approach to examine them. In such
cases, SPSS helps immensely.
SPSS is the finest tool for market researchers seeking for a dependable
solution to help them comprehend their data, evaluate trends, forecas t,
plan, and draw conclusions.
SPSS assists market researchers in extracting meaningful insights from
consumer data by employing advanced statistical analytics. It is possible
to obtain precise information about market trends thanks to its strong
survey da ta analysis technologies.
There is also Psychographic segmentation, preference scaling, predictive
analysis, statistical learning, and a slew of other sophisticated techniques
including stratified, clustered, and multistage sampling are all available
throu gh the application of SPSS.
Education
Every year, educational institutions face the challenge of enrolling and
keeping students. Not to mention the fact that they must recruit new pupils
each year. SPSS has large use over here. munotes.in
Page 121
Introduction to SPSS
121 SPSS software is presently u sed by more than 80% of all institutions in the
United States.
The capacity of SPSS software to focus on trends allows them to predict a
student's future achievement. It employs a number of indicators to identify
pupils who are at risk.
The university can utilize SPSS software to analyze a wide range of
complicated data sets in order to reveal hidden patterns.
Healthcare
To deliver excellent healthcare, we must address a number of concerns.
Some of the most serious concerns in healthcare organizations are o bsolete
patient delivery techniques and unbalanced incentives for caregivers. This
is where analytics can literally save millions of life. There are several
applications for using SPSS statistical analysis in healthcare delivery.
When it comes to the healt hcare industry, patient data is very important.
Not only can bad data have disastrous consequences, but it is also timely,
sensitive, and rapid.
Healthcare businesses can use SPSS to develop a patient delivery program
based on data. It will not only improv e patient outcomes but will also save
costs.Univariate and multivariate analysis are used for data sets with
complicated connections.
Retail
Analytics are frequently used in the retail business for everything from
initial stock planning to anticipating fut ure trends. Customers have a lot of
options when it comes to retail merchandise now that social media,
forums, and review sites have emerged.
Customers make purchasing selections based on internet reviews about the
brand. As a result, it is critical that r etail firms provide the finest service
possible. Fortunately, statistical analysis can save the retail business.
Data generated by retail enterprises must be gathered, evaluated, and
translated into meaningful insights. Businesses will provide exceptional
customer experiences if they use data successfully with SPSS software.
SPSS analysis enables merchants to better understand their consumers,
supply them with the best solutions, and distribute them through the most
effective channels.
SPSS analysis may hel p you understand anything from how various client
groups act to why they make particular purchasing decisions.
SPSS statistics will profile clients based on historical expenditure and
behavior trends. It will generate consumer preferences and provide a stu dy munotes.in
Page 122
Quantitative Social
Research
122 of what causes customers to convert from casual visitors to shoppers by
utilizing this data.
12.10 BEGINNING WITH SPSS
SPSS Installation Guide -
Start – All programs – SPSS Inc – SPSS 16.0, then double -click the icon
to launch SPSS.
First and foremost , we must review the minimal system requirements at
SPSS Statistics System Requirements.
The selection then identifies the operating system installed on your
machine and determines the prerequisites.
Open a browser and navigate to the SPSS website, which w ill result in the
download of the software application. Begin with the free trial version of
SPSS.
A Data Editor window with Data View and Variable View would open by
default. The first thing when we open SPSS is the Data Editor where we
add data, edit, mo dify, save, we can also define etc. Like in Excel sheet we
have a display window. The second thing to understand is the output
Viewer where one can see the output the finishing. There are sample packs
available where you may practice learning.
Variable Vie w
1. Name: This is a column field that accepts the unique ID. This aids in
data sorting. For example, different demographic characteristics
such as name, gender, age, and educational degree can be used to
sort data. The sole restriction is that special chara cters are not
permitted in this kind.
2. Label: As the name implies, it provides the label. This also allows
for the addition of special characters.
3. Type: This is particularly important when inserting various types of
data.
4. Width: Character length may be meas ured.
5. Decimal: When inputting a percentage figure, this type helps us
determine how many digits are necessary following the decimal.
6. Value: This assists the user in entering the value.
7. Missing: This allows the user to skip over superfluous data during
analysis.
8. Align: As the name implies, alignment aids in left or right
alignment. However, in this situation, for example, left align.
9. Measure: This aids in the measurement of data entered into
instruments such as ordinal, cardinal, and nominal. (Refer image 1) munotes.in
Page 123
Introduction to SPSS
123
Image 1 - The above given image shows the screenshot of Variable page.
The data must be entered into the "variable view" page. It enables us to
adapt the data type as needed for analysis.
In short, to evaluate the data, fill out the various column hea ders such as
Name, Label, Type, Width, Decimals, Values, Missing, Columns, Align,
and Measures.
These headers represent the many aspects that assist to characterize the
data.
Data Viewing -
The data display is organized into rows and columns. We can opera te with
SPSS by importing a file or manually entering data.
Procedure for importing EXCEL files into that of SPSS
The first step is to select File.
=> Click to open
=> Choose Data
=> Dialog Box
=> Type files
.xls spreadsheet munotes.in
Page 124
Quantitative Social
Research
124 After selecting the excel fil e to be imported for data analysis, we must
verify that the "read variable names from the first row of data" option is
chosen in the dialogue box.
Finally, press the OK button. SPSS has now imported your file.
Image2 - shows the importing procedure of Ex cel file into SPSS
Analyzing Data
Once, the Data sets are imported or feeded into the SPSS software the
specific commands have to give and depending upon that the data is
generated. One can even get a graphical kind of a data like charts, pie
diagram etc. The following are some of the images which would help you
understand this in pictorial format. At the endnote of the chapter there is
also a YouTube video link provided where you could see the video of how
to do the data analysis. (Refer image 2)
Dependi ng upon the required output of the series of questions and the
derived answers of the subject. The data can be produced in the required
form like Pie chart, Bar chart etc. and can be seen in the output viewer.
munotes.in
Page 125
Introduction to SPSS
125
Image 3 – In the above given procedure in the images explains the data
analysis procedure.
12.11 LIMITATIONS OF SPSS
Unlike anyother other research tool SPSS too has some limitations like -
If researchers gather data using inaccurate or biased procedures, the
statistical analysis that result s will not provide accurate results. There is no
problem if the difference between the sample and the real population is
insignificant. However, if the discrepancy is significant, the results will be
deceptive.
The SPSS analysis will not fail if researcher s do not measure the specific
thing they intend to assess. Another problem with utilizing a statistical
analysis program like SPSS is that you wind up with easy answers to
complicated problems.
Check Your Progress
1. List out two uses of SPSS
2. Discuss on e limitation of SPSS.
munotes.in
Page 126
Quantitative Social
Research
126 12.12 SUMMARY
The use of computers and software’s has made the research faster in social
sciences than ever before. In this chapter, we learnt about one such
software called SPSS a statistical software which can analyze data at a
very faster pace, especially large amount of data. Often SPSS is used in
quantitative research -based studies. While Excel is useful for data
organization, SPSS is better suited for in -depth data analysis. This tool is
quite handy for data analysis and visuali zation. We also saw, the uses of
SPSS in several fields like medicine, retails etc. We also discussed about
certain limitation like if error is at the data collection point then the output
could be different.
12.13 QUESTIONS
1. Discuss SPSS uses and its limitations.
2. Discuss the functions of SPSS
12.14 REFERENCES
1. https://johnnoels.medium.com/what -is-spss-and-its-importance -in-
research -data-analysis -5f109ab90da1
2. https://www.spss -tutorials.com/ spss-what -is-it/
3. https://lo.unisa.edu.au/mod/book/view.php?id=646443&chapterid=1
06606https://www.alchemer.com/resources/blog/what -is-spss/
4. https://surveysparrow.com/blog/what -is-spss/
5. https://johnnoels.medium.com/what -is-spss-and-its-importance -in-
research -data-analysis -5f109ab90da1
munotes.in