Table Of Content?
Research Methods For Library Science
Subject: RESEARCH METHODS FOR LIBRARY SCIENCE Credits: 4
SYLLABUS
Meaning of Research; Objectives of Research; Types of Research; Research Approaches;
Significance of Research; Research and Scientific Method; Importance of knowing how
Research is done; Research Process; Problems Encountered by Researchers in India; Meaning of
Research Design; Need for Research Design; Important Concept Relating to Research Design;
Different Research Designs; Basic Principles of Experimental Designs; Developing a Research
Plan.
Need for Sampling; Important Sampling Distributions; Sampling Theory; Interpretation; Why
Interpretation; Techniques of Interpretations; Precaution in Interpretation; Report Writing;
Interviewing Techniques; Understanding Surveys; Questionnaire Design; Receiving Completed
Questionnaires; Data Gathering and Analysis Techniques; Collection of Data; Evaluate and
Analyze the Data.
Content Analysis: Analysis and Size; Questioning the Content; Qualitative and Quantitative
Analysis; Anatomy of an on-line Focus Group; Affinity Groups; Internet Audience Research
Analyzing Online Discussions: Ethics; Data and Interpretation; Reporting the Findings.
Suggested Readings:
1. Media and Communication Research Methods: an Introduction to Qualitative and
Qualitative Methods; Arthur A; Sage Publications.
2. Mass Media Research: An Introduction ; Roger D. Wimmer; Joseph R. Dominick;
CengageBrain.com
3. Media Research Techniques; Arthur Asa Berger; Sage Publications.
CONTENT
Lesson No. Topic Page No.
Lesson 1 Introduction - what is research 1
Lesson 2 Research Design 4
Lesson 3 Research Planning 7
Lesson 4 Audience Research etc. - I 12
Lesson 5 Audience Research etc. - II 16
Lesson 6 Sampling 21
Lesson 7 Sampling - Multi-stage Sampling 25
Lesson 8 Questionnaires 29
Lesson 9 Question Formats 34
Lesson 10 Fieldwork 39
Lesson 11 Interview - Prepare Interviewer Instructions 46
Lesson 12 Feildwork 49
Lesson 13 Interviewing 53
Lesson 14 Survey 56
Lesson 15 Survey – Telephonic Survey 59
Lesson 16 Surveys- Mail Survey 63
Lesson 17 Survey – Survey Presentation 67
Lesson 18 Checking and Editing Surveys 71
Lesson 19 Case Study 74
Lesson 20 Content Analysis 79
Lesson 21 Content Analysis - Analysis and Size 82
Lesson 22 Content Analysis- Questioning the Content 86
Lesson 23 “Qualitative” and “Quantitative” 90
Lesson 24 Anatomy of an on-line focus group 96
Lesson 25 Group Discussions 99
Lesson 26 Affinity Groups 104
Lesson 27 Internet Audience Research 110
Lesson 28 Analyzing Online Discussions: Ethics, Data and Interpretation 114
Lesson 29 Reporting the findings 118
Lesson 30 Reporting the Findings - The form of TV Programs 121
CONTENT
Lesson No. Topic Page No.
Lesson 31 Copyright Act- 1957 127
Lesson 32 Using research well 138
Lesson 33 Are All Polls Valid? 142
LESSON 1:
INTRODUCTION - WHAT IS RESEARCH
Topics Covered - the white-coated scientist bent over a bubbling test tube. This
Meaning, Nature, Objectives, Significance, Importance, fits well the Chambers definition. In contrast, the ‘collate old
Overview facts’ definition suggests heads bent over old manuscripts in
the British Library Reading Room.
Objectives
Upon completion of this Lesson, you should be able to: These are just two types of research, we’ll consider a few more
ideas, but you may have thought of something different again.
• Understand what is research
The first of this list , the scientist, is perhaps the archetypal
• Identify the Objectives and Functions of Research
image of experimental research. Of course, the white coated
• Identify the Significance and importance of research
technician is less well respected today than in the late 60’s when
We will first ask what research is and whether, you ought to be Thunderbirds was first screened. A more acceptable modern
doing it anyway. After this, and forming the bulk of the image might be the botanist in the Amazonian rain forest,
document, we shall look at the process of research itself. observing and discovering new creatures before they fall under
the axe and are consumed by fire. Behavioural and experimental
psychologists would also fall under this general heading.
The social scientist’s methods are different from the laboratory
(although quite similar to the botanist). They include inter-
views, observation and the collection of data. All of which will
be needed at very least during your requirements elicitation from
your client. Notice how the world of the social scientist is far
less controlled than that of the laboratory or even the botanist.
Pause for a moment, think of the word ‘research’ - what images You can put a beetle in a ‘bug box’ and examine it, but social
come into your mind? Don’t try to define it, just think about situations collapse when dissected too closely. The ecologist has
what it means to you. Write down a few ideas below. similar problems.
Historical research corresponds to the British Library image,
reading original sources and other peoples books and papers.
Of course it does not stop there. The aim of the historian is to
understand the historical processes as well as to record it. One
of the key things a historian has to recognise is that all the
sources are biased - written from a particular perspective by a
particular person for some particular purpose. You will be faced
with similar issues, albeit from modern sources.
Journalists operate in a somewhat similar fashion. They do not
expect to generate new knowledge (although they may occasion-
ally generate fiction). Instead, they cull from exiting sources:
people, books, other newspaper articles etc., in order to write
Look at the two dictionary definitions above. Which one, if about their chosen subject. Note the range of sources they must
either, is closest to your images of research? The first is more draw on. Also note that they will not attempt to thoroughly
lofty - looking for totally new knowledge. The Oxford defini- understand the subject they are writing about, nor do they
tion also includes the collation of existing knowledge. The attempt total coverage of the area. They have a goal, to write an
image, which immediately springs to my mind when I think of article, and they find out just enough to do that job. The
research although not what I do) is of Brains on Thunderbirds academic must take a deeper and wider perspective than this,
1
but do not underestimate the skill of the journalists. When cant academic work before hand and analysis of your results
some event happens they have to find out enough within a few after. One would hope that this will also contribute to making
hours to be able to write cogently about it. the project interesting.
Finally we have industrial Research and Development. What is To be integrative and intellectually challenging the project must
the research element in it? Well, some firms do have ‘blue skies’ clearly involve research in the sense of ‘collating old facts’. That
research laboratories whose job is to find exciting new things, is, aspects of the British Library image combined with the
rather like (but better resourced) than a University research focused attitude of industrial R & D.
atmosphere. However, most do not have sufficient spare But, the crunch, should the project be innovative - breaking new
resources to use for this sort of enterprise. Instead, the job of ground, extending the sum of human knowledge, generating
the commercial researcher is to draw on existing knowledge and new and novel solutions?
bring it to bear on a particular problem. This may involve
Well, it would obviously be nice to develop some new algo-
creating something new, but usually by some adaptation of an
rithm or discover some new fact about IT, and the best projects
existing solution. Like the journalist, the industrial researcher is
will involve some level of innovation, but this is an under-
very goal directed, but has to do more. The journalist merely
graduate and not a research degree, so it is not necessary. On the
has to gather enough information to write the article, the
other hand, it would be hard to apply even standard techniques
industrial researcher must understand the information in order
to a new problem without there being something novel about
to apply it to a new situation, that is, the product under
it. Every situation is slightly different and you will have to use a
development.
level of ingenuity (another ‘I’ word) in dealing with it.
Clearly, the R & D situation is closest to your project as you too
So, given you should be doing some research, how do you go
have a client and a product to produce. However, the situation
about it? You all know the old saying: “you should learn from
is not identical. Your aim is not only to produce a product, but
your mistakes”. Indeed, this will be an important part of your
also to obtain a degree. Although your time may hardly seem
final report. You will have to reflect upon what did and did not
leisurely, you do in fact have more ‘leisure’ to reflect upon the
work. You will be expected to diagnose your problems and
work you are doing, taking a more academic angle. In particular,
learn from them. However, you do not have enough time to
this might mean being somewhat broader in your searches for
make too many mistakes, so you should avoid as many as
information and considering more alternatives to a problem,
possible.
even after you have found a solution, which works.
So, given these definitions of research and examples of
researchers, should you be doing research in your project, or
should that be left to the PhD students and academics. And, if
you should be doing research, which of the above types should
it be.
How do you avoid making your own mistakes? Well although
it is good to learn from your own mistakes, it is shrewd to learn
from other peoples mistakes. Find out what other people have
done right and done wrong before making the same mistakes
or even working hard to discover the same good things.
To do this you must study other people’s work before embark-
Let’s think about your project in terms of some ‘I’ words. First ing on your own - that is, more research. But it is not all of the
it should be integrative, bringing together knowledge from British Library kind.
different areas. In most of your courses you consider some
particular aspect of computing, business or mathematics. In
your project you must use knowledge from a variety of areas
and sources. Some things you may already know from a course
you have done. Other things might need further investigation.
The project is an independent piece of work which is interesting
to you. As it is YOU doing the work, you are only expected to
produce what is reasonable for a final year undergraduate.
However, as it as an academic project, part of an honours
degree, it must also be intellectually challenging. Again, not the
minimal solution to a problem, but one that involves signifi-
2
You obviously need to read what other people have written: activities, none of these activities can be understood without
books, academic papers, newspaper articles etc. In addition you placing them in the wider context of his entire life.
need to consider what they say by interviews, discussions etc. In experimental design, the researcher can often exert a great deal
Finally, examine what they make - in your context primarily of control over extraneous variables and thus ensure that the
software, but also possibly the organisational structures, paper stimuli in the experimental conditions are similar. In a labora-
based systems etc. tory experiment, one has the opportunity to vary the treatment
Assumptions of scientific method David Easton has laid down in a systematic manner, thus allowing for isolation and precise
certain assumptions and objectives of scientific method. They specification of the important difference.
are regularities, verification, techniques, quantification, values
Assignments
systematisation, pure science, and integration.
1. The task of defining the research problem often follows a
1. Regularities sequential pattern. Explain?
Scientific method believes that the world is regular and phe-
2. What do you mean by research? Explain its significance in
nomena occur in patterns. Further there are discernible
modern times?
uniformities in political and social behaviour which can8be
expressed as generalisation which are capable of explaining and
predicting political and social phenomena.
2. Verification
Scientific method presupposes that knowledge should consist
of propositions that have been subjected to empirical tests, and
that all evidence must be based on observation.
3. Techniques
Scientific method attaches a great deal of importance to the
adoption of correct techniques for acquiring and interpreting
data. In order to make the research self conscious and critical
about the methodology, there is a need for the use of sophisti-
cated tools-like multivariate analysis, sample survey and
mathematical models, simulation and so on.
4. Quantification
Science necessarily involves mathematical formulas and measure-
ments. Theories are not acceptable if they are not expressed in
mathematical language. All observations must ‘be quantified
because quantification has advantages in terms of precision and
manageability.
5. Values
Values and facts are. two separate things. Science, it is claimed, is
value free. It is not concerned with what is “good”, “right”,
“proper” “desirable” etc. “Good” and “bad” is the concern of
philosophers. Scientific enquiry to be objective, therefore, must
be value free.
6. Systematisation
Scientific study demands that research should be systematic. it
means that it must be theory-oriented and theory directed. The
theory and research should form interrelated parts of a coherent
and orderly body of knowledge.
7. Pure Science
Scientific minded social scientists insist on pure science ap-
proach. They agree that theoretical understanding may lead to an
application of this knowledge to problems of life. Both the
theory and its application are parts of.scientific enterprise.
8. Integration
Finally, there is the question of integration of each social science
with other social sciences. The behaviouralists agree that man is
a social animal and while one may try to draw boundary lines
between the social, political, economic, cultural and other
3
LESSON 2:
RESEARCH DESIGN
Topics Covered conventional approach is to put the research question in writing
Research Design, importance, principles, Approaches in the introduction of a report starting with the phrase “ The
purpose of this study is . . . .” This approach forces the
Objectives
researcher to:
Upon completion of this Lesson, you should be able to:
a. identify the research objective (allows others to benchmark
• What is research design
how well the study design answers the primary goal of the
• Identify the importance of research design
research)
• Know the principles of RD
b. identify key abstract concepts involved in the research
• Different Research approaches
Abstract concepts: The starting point for measurement.
The objective of science is to explain reality in such a fashion so Abstract concepts are best understood as general ideas in
that others may develop their own conclusions based on the linguistic form that help us describe reality. They range from the
evidence presented. The goal of this handbook is to help you simple (hot, long, heavy, fast) to the more difficult (responsive,
learn how to conduct a systematic approach to understanding effective, fair). Abstract concepts should be evident in the
the world around us that employs specific rules of inquiry; what research question and/or purpose statement. An example of a
is known as the scientific model. research question is given below along with how it might be
The scientific model helps us create research that is quantifiable reflected in a purpose statement.
(measured in some fashion), verifiable (others can substantiate Research Question: Is the quality of public sector and private
our findings), replicable (others can repeat the study), and sector employees different?
defensible (provides results that are credible to others—this
Purpose statement: The purpose of this study is to determine
does not mean others have to agree with the results). For many
if the quality of public and private sector employees is different.
the scientific model may seem too complex to follow, but it is
often used in everyday life and should be evident in any research 2. Develop Theory
report, paper, or published manuscript. The corollaries of A theory is one or more propositions that suggest why an
common sense and proper paper format with the scientific event occurs. It is our view or explanation for how the world
model are given below. works. These propositions provide a framework for further
analysis that are developed as a non-normative explanation for
Corollaries among the Scientific Model, Common Sense, and
“What is” not “What should be.” A theory should have logical
Paper Format
integrity and includes assumptions that are based on para-
digms. These paradigms are the larger frame of contemporary
Paper understanding shared by the profession and/or scientific
Scientific Model Common Sense
Format community and are part of the core set of assumptions from
Research Question Why Intro which we may be basing our inquiry.
Develop a theory Your answer Intro
3. Identify Variables
Identify variables How Method
Variables are measurable abstract concepts that help us describe
Identify Expectations Method
relationships. This measuring of abstract concepts is referred to
hypotheses
as operationalization. In the previous research question “Is the
Test the Collect/analyze data Results
quality of public sector and private sector employees different?”
hypotheses
the key abstract concepts are employee quality and employment
Evaluate the results What it means Conclusion
sector. To measure “quality” we need to identify and develop a
Critical review What it doesn’t Conclusion
measurable representation of employee quality. Possible quality
mean
variables could be performance on a standardized intelligence
test, attendance, performance evaluations, etc. The variable for
Overview of First Four Elements of the employment sector seems to be fairly self-evident, but a good
Scientific Model researcher must be very clear on how they define and measure
The following discussion provides a very brief introduction to the concepts of public and private sector employment.
the first four elements of the scientific model. Variables represent empirical indicators of an abstract concept.
However, we must always assume there will be incomplete
1. Research Question
congruence between our measure and the abstract concept. Put
The research question should be a clear statement about what
simply, our measurement has an error component. It is unlikely
you intend to investigate. It should be specified before research
is conducted and openly stated in reporting the results. One
4.
to measure all aspects of an abstract concept and can best be
understood by the following: Variable Level
Abstract concept = indicator + error Country Nominal
Because there is always error in our measurement, multiple
Letter Grade Ordinal
measures/indicators of one abstract concept are felt to be better
Age Ratio
(valid/reliable) than one. As shown below, one would expect
that as more valid indicators of an abstract concept are used the Temperature Interval
effect of the error term would decline:
Abstract concept = indicator1 + indicator2 + indicator3 + error
Reliability and Validity
Levels of Data
The accuracy of our measurements are affected by reliability and
There are four levels of variables. These levels are listed below in
validity.R eliability is the extent to which the repeated use of a
order of their precision. It is essential to be able to identify the
measure obtains the same values when no change has occurred
levels of data used in a research design. They are directly
(can be evaluated empirically). Validity is the extent to which
associated with determining which statistical methods are most
the operationalized variable accurately represents the abstract
appropriate for testing research hypotheses.
concept it intends to measure (cannot be confirmed empirically-
Nominal: Classifies objects by type or characteristic (sex, race, it will always be in question). Reliability negatively impacts all
models of vehicles, political jurisdictions) studies but is very much a part of any methodology/
Properties operationalization of concepts. As an example, reliability can
depend on who performs the measurement (i.e., subjective
1. categories are mutually exclusive (an object or characteristic
measures) and when, where, and how data are collected (from
can only be contained in one category of a variable)
whom, written, verbal, time of day, season, current public
2. no logical order
events).
Ordinal: classifies objects by type or kind but also has some
There are several different conceptualizations of validity.
logical order (military rank, letter grades)
Predictive validity refers to the ability of an indicator to
Properties correctly predict (or correlate with) an outcome (e.g., GRE and
1. categories are mutually exclusive performance in graduate school). Content validity is the extent
to which the indicator reflects the full domain of interest (e.g.,
2. logical order exists
past grades only reflect one aspect of student quality). Construct
3. scaled according to amount of a particular characteristic they
validity (correlational validity) is the degree to which one
possess
measure correlates with other measures of the same abstract
Interval: classified by type, logical order, but also requires that concept (e.g., days late or absent from work may correlate with
differences between levels of a category are equal (temperature in performance ratings). Face validity evaluates whether the
degrees Celsius, distance in kilometers, age in years) indicator appears to measure the abstract concept (e.g., a
Properties: person’s religious preference is unlikely to be a valid indicator of
employee quality).
1. categories are mutually exclusive
2. logical order exists 4. Identify Measurable Hypotheses
A hypothesis is a formal statement that presents the expected
3. scaled according to amount of a particular characteristic they
relationship between an independent and dependent variable. A
possess
dependent variable is a variable that contains variations for
4. differences between each level are equal
which we seek an explanation. An independent variable is a
5. no zero starting point variable that is thought to affect (cause) variations in the
Ratio: same as interval but has a true zero starting point dependent variable. This causation is implied when we have
(income, education, exam score). Identical to an interval-level statistically significant associations between an independent and
scale except ratio level data begin with the option of total dependent variable but it can never be empirically proven: Proof
absence of the characteristic. For most purposes, we assume is always an exercise in rational inference.
interval/ratio are the same.
Association
The following table provides examples of variable types: Statistical techniques are used to explore connections between
independent and dependent variables. This connection between
or among variables is often referred to as association. Associa-
tion is also known as covariation and can be defined as
measurable changes in one variable that occur concurrently with
changes in another variable. A positive association is repre-
sented by change in the same direction (income rises with
education level). Negative association is represented by
concurrent change in opposite directions (hours spent exercising
5
and % body fat). Spurious associations are associations 4. Trend study: tracking indicator variables over a period of
between two variables that can be better explained by a third time (unemployment, crime, dropout rates)
variable. As an example, if after taking cold medication for
seven days the symptoms disappear, one might assume the
medication cured the illness. Most of us, however, would
probably agree that the change experienced in cold symptoms
are probably better explained by the passage of time rather than
pharmacological effect (i.e., the cold would resolve itself in
seven days irregardless of whether the medication was taken or
not).
Causation
There is a difference between determining association and
causation. Causation, often referred to as a relationship, cannot
be proven with statistics. Statistical techniques provide evidence
that a relationship exists through the use of significance testing
and strength of association metrics. However, this evidence
must be bolstered by an intellectual exercise that includes the
theoretical basis of the research and logical assertion. The
following presents the elements necessary for claiming causa-
tion:
External and Internal Validity
There are two types of study designs, experimental and quasi-
experimental.
Experimental: The experimental design uses a control group
and applies treatment to a second group. It provides the
strongest evidence of causation through extensive controls and
random assignment to remove other differences between
groups. Using the evaluation of a job training program as an
example, one could carefully select and randomly assign two
groups of unemployed welfare recipients. One group would be
provided job training and the other would not. If the two
groups are similar in all other relevant characteristics, you could
assume any differences between the groups employment one
year later was caused by job training.
Whenever you use an experimental design, both the internal
and external validity can become very important factors.
Internal validity: The extent to which accurate and unbiased
association between the IV and DVs were obtained in the study
group.
External validity: The extent to which the association between
the IV and DV is accurate and unbiased in populations outside
the study group.
Quasi-experimental: The quasi-experimental design does not
have the controls employed in an experimental design (most
social science research). Although internal validity is lower than
can be obtained with an experimental design, external validity is
generally better and a well designed study should allow for the
use of statistical controls to compensate for extraneous
variables.
Types of Quasi-experimental Design
1. Cross-sectional study: obtained at one point in time (most
surveys)
2. Case study: in-depth analysis of one entity, object, or event
3. Panel study: (cohort study) repeated cross-sectional studies
over time with the same participants
6
Description:Assumptions of scientific method David Easton has laid down certain assumptions and Mehndi, Aamir Khan, Aishwarya. **. Robin Singh, Anil.