10/18/2014

Research Process (in previous Lecture . . .)

FF
Review the literature
.
Research Process: Review
FF

A Brief Description Concepts

And
Design
Research Collect Interpret
Define theories Formulate Analyse
(Including Data and
Research hypothesis Data
Sample report
Problem
Review Design)
F F
PhD Course Work -2014 Previous
Research
I III IV V VI VII
findings
Research Methodology
Instructor: Dr. G. L. Prajapati
Prajapati,, IET-
IET-DAVV II
F
F Feed Back
FF Feed Forward

Research Process
The order concerning various steps for a useful procedural

•
guideline regarding the research process:
Formulating the research problem;
Defining a
• Extensive literature survey;
•
•
Developing the hypothesis;
Preparing the research design;
Research Problem
• Determining sample design;
• Collecting the data;
• Execution of the project;
• Analysis of data;
• Hypothesis testing;
• Generalisations and interpretation, and
• Preparation of the report or presentation of the results, i.e., Formal
write-up of conclusions reached.

1
 10/18/2014

• State the components of a research problem as

under:
– an individual or a group which has some
difficulty or the problem.
• To define a problem – some objective(s) to be attained at.
correctly, a researcher must • If one wants nothing, one cannot have a
problem.
know: – Must be alternative means (or the courses of
action) for obtaining the objective(s) one
–What a problem is? wishes to attain
• There must be at least two means available
to a researcher for
• if he has no choice of means, he cannot
have a problem.

• State the components of a research

problem as under:
– There must remain some doubt in the • SELECTING THE PROBLEM
mind of a researcher with regard to the – The research problem undertaken for study
selection of alternatives. must be carefully selected.
• This means that research must – The task is a difficult one, although it may not
answer the question concerning the appear to be so.
relative efficiency of the possible
alternatives.
– There must be some environment(s) to
which the difficulty pertains.

2
 10/18/2014

• SELECTING THE PROBLEM • SELECTING THE PROBLEM

– Subject which is overdone should not – Contact an expert or a professor in the
be normally chosen, for it will be a University who is already engaged in
difficult task to throw any new light in research.
such a case. – Read articles published in current
– Controversial subject should not literature available on the subject and
become the choice of an average may think how the techniques and ideas
researcher.
discussed there in might be applied to
– Too narrow or too vague (fuzzy) the solution of other problems.
problems should be avoided.
– The subject selected for research – Discuss with others what he has in mind
should be familiar and feasible so that concerning a problem. In this way he
the related research material or sources should make all possible efforts in
of research are within one’s reach. selecting a problem.

• SELECTING THE PROBLEM

– The importance of the subject, the qualifications and the
training of a researcher, the costs involved, the time factor • TECHNIQUE IN DEFINING A PROBLEM
• Whether he is well equipped in terms of his background
to carry out the research? – Statement of the problem in a general way;
• Whether the study falls within the budget he can afford? – Understanding the nature of the problem;
• Whether the necessary cooperation can be obtained – Surveying the available literature
from those who must participate in research as
subjects? – Developing the ideas through discussions;
– The selection of a problem must be preceded by a and
preliminary study. This may not be necessary when the
problem requires the conduct of a research closely similar
– Rephrasing the research problem into a
to one that has already been done. working proposition.
• But when the field of inquiry is relatively new and does
not have available a set of well developed techniques, a
brief feasibility study must always be undertaken.

3
 10/18/2014

• (i) Statement of the problem in a general way:

• (ii) Understanding the nature of the problem:
– the problem should be stated in a broad
– Understand its origin and nature clearly
general way, keeping in view either some
– to discuss it with those who first raised it in
practical concern or some scientific or
order to find out how the problem originally
intellectual interest. came about and with what objectives in view
– In case of social research, it is considered – A discussion with those who have a good
advisable to do some field observation, some knowledge of the problem concerned or
sort of preliminary survey or what is often similar other problems.
called pilot survey. – The researcher should also keep in view the
– Then the researcher can himself state the environment within which the problem is to be
problem or he can seek the guidance of the studied and understood.
guide or the subject expert in accomplishing
this task.

• (iii) Surveying the available literature: • (iv) Developing the ideas through discussions:
– All available literature concerning the problem must
necessarily be surveyed and examined – Often produces useful information
• It will be well-conversant (Familiar with or – Various new ideas can be developed
knowledgeable about something)with relevant – Discuss problem with colleagues and others who
theories in the field, reports and records have enough experience in the same area or in
• To find out what data and other materials -- working on similar problems --- known as an
“Knowing what data are available often serves to experience survey.
narrow the problem itself as well as the technique
that might be used.” – People with rich experience are in a position to
• If there are certain gaps in the theories, or whether enlighten the researcher on different aspects of
the existing theories applicable to the problem his proposed study and their advice and
under study are inconsistent with each other, or comments are usually invaluable (Extremely
whether the findings of the different studies do not useful) to the researcher --- sharpen his focus of
follow a pattern consistent with the theoretical
expectations and so on. attention on specific aspects within the field.
• for indicating the type of difficulties that may be
encountered in the present study as also the
possible analytical shortcomings.

4
 10/18/2014

• (v) Rephrasing the research problem: • The following points must also be
– to rephrase the research problem into a observed while defining a research
working proposition problem:
– (a) Technical terms and words or phrases,
– rephrasing the problem into analytical or
with special meanings used in the statement
operational terms is not a difficult task of the problem, should be clearly defined
– Through rephrasing, the researcher puts – (b) Basic assumptions or postulates (if any)
the research problem in as specific terms relating to the research problem should be
as possible so that it may become clearly stated
operationally viable and may help in the
development of working hypotheses

• An example :
• Defining a research problem: • Let us suppose that a research problem in a broad
– (c) A straight forward statement of the value of general way is as follows:
the investigation (i.e., the criteria for the – “Why is productivity in Japan so much higher than in
selection of the problem) India”?
– It has a number of ambiguities such as
– (d) The suitability of the time-period and the
• What sort of productivity is being referred to?
sources of data available
• With what industries the same is related?
- (e) The scope of the investigation or the limits • With what period of time the productivity is being
within which the problem is to be studied must talked about?
be mentioned explicitly in defining a research • In view of all such ambiguities the given statement
problem. or the question is much too general to be
amenable to analysis.

5
 10/18/2014

• Rethinking and discussions about the problem

may result in narrowing down the question to: • Example:
• Example – With this sort of formulation, the various terms
– “What factors were responsible for the higher involved such as ‘labour productivity’, ‘productivity
labour productivity of Japan’s manufacturing differentials’, etc. must be explained clearly.
industries during the decade 1971 to 1980 – The researcher must also see that the necessary data
relative to India’s manufacturing industries?” are available.
• Further rethinking and rephrasing might place – In case the data for one or more industries selected
the problem on a still better operational basis as are not available for the concerning time-period, then
shown below: the said industry or industries will have to be
– “To what extent did labour productivity in 1971 substituted by other industry or industries.
to 1980 in Japan exceed that of India in – The suitability of the time-period must also be
respect of 15 selected manufacturing examined. Thus, all relevant factors must be
industries?
considered by a researcher before finally defining a
– What factors were responsible for the research problem
productivity differentials between the two
countries by industries?”

– Defining a research problem is crucial in Sample Deductive and Inductive Arguments

defining the quality of the answers, and
determines the exact research method used. Example of Deduction Example of Induction
• major premise: • Boss to employee:
All professors like “Biff has a tattoo of
– A quantitative experimental design uses research an anchor on his
deductive reasoning to arrive at a testable • minor premise: arm. He probably
hypothesis. served in the Navy.”
• Dr NS Chaudhari is a
professor
– Qualitative research designs use inductive • Conclusion: Therefore,
reasoning to propose a research statement. Dr NS Chaudhari likes
research

6
 10/18/2014

Determining Sample Design

• Example
– An anthropologist might find references to a • Sampling may be defined as the selection of
relatively unknown tribe in Papua New Guinea.
some part of an aggregate or totality, on the
– Through inductive reasoning, she arrives at
basis of which a judgment or inference
the research problem and asks, ‘How do
these people live and how does their culture
about the aggregate or totality is made.
relate to nearby tribes?’ • In other words it is process of obtaining
– She has found a gap in knowledge, and she information about an entire population by
seeks to fill it, using a qualitative case study, examining only a part of it.
without a hypothesis

Need for Sampling Need for Sampling

Representative Sample

. 〈 〈 〈 the 〉 〈 〈 girl 〉 〉 〉 〈 〈 likes 〉 〈 〈 a 〉 〈 〈 cat 〉 〉 〉 〉 〉

Sampling is used in practice for a variety of S → NT 1 NT 2
NT 1 → NT 3 NT 4
reasons such as:- 〈 〈 〈 the 〉 〈 〈 girl 〉 〉 〉 〈 〈 likes 〉 〈 〈 a 〉 〈 〈 dog 〉 〉 〉 〉 〉 NT 4 → NT 5
1. Reduces the time and cost NT 4 → NT 6 NT 4
〈 〈 〈 a 〉 〈 〈 dog 〉 〉 〉 〈 〈 chases 〉 〈 〈 the 〉 〈 〈 girl 〉 〉 〉 〉 〉 NT 2 → NT 7 NT 1
2. saves labor NT 3 → the
3. Quality of a study is often better with 〈 〈 〈 a 〉 〈 〈 dog 〉 〉 〉 〈 〈 chases 〉 〈 〈 a 〉 〈 〈 cat 〉 〉 〉 〉 〉 NT 3 → a
NT 5 → girl
sampling than with a complete 〈 〈 〈 a 〉 〈 〈 dog 〉 〉 〉 〈 〈 chases 〉 〈 〈 a 〉 〈 〈 girl 〉 〉 〉 〉 〉 NT 5 → cat
[Link] NT 5 → dog
〈 〈 〈 the 〉 〈 〈 dog 〉 〉 〉 〈 〈 chases 〉 〈 〈 a 〉 〈 〈 young 〉 〈 〈 girl 〉 〉 〉 〉 〉 〉. NT 6 → young
5. Provides much better results NT 7 → likes
6. Only procedure possible, if the population is NT 7 → chases.
infinite.

7
 10/18/2014

There are many types of sampling, a) Probability sampling:-

most sampling types can be is one in which every unit in the
categorized as: population has a chance ( greater than
Zero) of being selected in the sample,
and this probability can be accurately
a) Probability sampling and determined. The combinations of these
b) Non-probability sampling traits make it possible to produce
unbiased estimates of population totals,
by weighing sampled units according to
their probability of selection.

Non-Probability sampling:
Probability Sampling is of the
following types:
• Non probability sampling plans are those
[Link] Random sampling that provide no basis for estimating how
[Link] Random sampling closely the sample characteristics
approximate the parameters of the
[Link] Random sampling population from which the sample was
4. Cluster/ Area sampling obtained. In fact the investigator is
[Link] stage sampling generally unable to identify the parent
population.

8
 10/18/2014

Non-Probability sampling may be

Simple Random sampling: -
classified into:-
[Link] or Accidental sampling A simple random sample is one in which each
element of the population has an equal and
[Link] or judgment sampling independent chance of being included in the sample
i.e.
[Link] sampling a sample selected by randomization method is
known as simple random sample and this technique
[Link] – ball sampling is simple random-sampling. Randomization is a
method and is done by using a number of
techniques as:-
a)Tossing a coin
b)Throwing a disc
c)Lottery method

Systematic Sampling:
The Fish Bowl Draw:
The simplest and most familiar type of Systematic sampling relies on arranging the
sample selection consists of putting numbers on target population according to some
slips of paper or marbles and depositing them in
ordering scheme and then selecting
a large container. The numbers identify and stand
for specific elements in the populations and elements at regular start and then proceeds
presumably the entire population of elements with the selection of every Kth element from
has been numbered and is represented in the the onwards. It is important that the starting
bowl. After mixing the thoroughly, the point is not automatically the first in the list,
investigator selects one number at a time, but is instead randomly chosen from within
blindfolded until the desired sample size is the first to the Kth element in the list.
obtained. This is called a random sample.
35

9
 10/18/2014

Example Stratified Sampling

A simple eg:- would be to select every 10th It is an improvement over the earlier method,
when employing this techniques, the
name from the telephone directory (an every researcher divides his population in strata on
10th sample, also referred to as sampling the basis of some characteristics, and from
with a skip of 10). each of these smaller homogenous groups
(strata) sample items are selected at random a
pre-determined number of Units. Researcher
should choose that characteristic or criterion
which seems to be more relevant in his
research work. Can be applied to obtain
representative sample when population does
not constitute a homogeneous group.

Cluster sampling: Multi-stage sampling: -

To select the intact group as a whole is known as a In this method, sampling is carried out in two or
cluster sampling. In cluster sampling the sample more stages. The population is regarded as being
units contain groups of elements (clusters) instead of composed of a number of first stage sampling units.
individual members or items in the population. Each of them is made up of number of second stage
• Example:- Suppose some departmental store units and so forth. That is, at each stage, a sampling
wishes to sample its credit card holders. It has unit is a cluster of the sampling units of the
issued its cards to 15,000 customers. The sample subsequent stage, first, a sample of the first stage
size is to be kept say 450. For cluster sampling sampling is drawn, and then from each of the
this list of 15,000 card holders could be formed selected first stage sampling unit, a sample of the
into 100 clusters of 150 card holders each. Three second stage sampling units is drawn. The
clusters might then be selected for the sample procedure continues down to the final Sampling units
randomly. or population elements. Appropriate random
sampling method is adopted at each stage.

10
 10/18/2014

Non- probability sampling

USAGE
methods :
Multi-stage sampling is appropriate where Convenience or accidental sampling: It means
selecting sample units in a ‘1 hit and miss fashion’.
the population is scattered over a wider Example: interviewing people whom we happen to
geographical area and no frame or list is meet. This sampling also means selecting whatever
available for sampling. It is also useful when sampling units are conveniently available.
a survey has to be made within a limited Example: A teacher may select students in his class.
time and cost budget. This method is also known as accidental
sampling because the respondents whom the
researcher meets accidentally are included in the
sample.

Purposive or Judgment
Quota Sampling:
Sampling:
• This is a form of convenient sampling involving selection of
• This method means deliberate selection of quota groups of accessible sampling units by traits such as
sample units that conform to some pre- Sex, Social class etc. In specific proportions, each
investigator may be given an assignment of quota groups
determined criteria. This is also known as specified by the pre-determined traits in specific proportions.
He can then select accessible persons belonging to those
judgment sampling. This involves selection groups in the area assigned to him.
of cases which we judge as the most • Quota sampling is therefore, a method of stratified sampling in
appropriate ones for the given study. It is which the selection within strata is non-random. Quota
sampling is used in studies like marketing survey, opinion
based on the judgment of the researcher polls, and readership survey which do not aim at precision but
to get quickly some crude results.
or some expert. It does not aim at
searching a cross section of a population.

11
 10/18/2014

Snow ball sampling: Is a technique of building up

a list or a sample of a special population by using an initial
set of its members as informants. For example a
researcher wants to study the problem faced by Indians in
another country, Say, he may identify an initial group of
Indians through some source like Indian Embassy, Then he
can ask each one of them to supply names of other
Indians known to them and continue this procedure until
he gets an exhaustive list from which he can draw a
sample or make a census survey.
This sampling technique may also be used in
socio-metric studies. For example, the members of a
social group may be asked to name the persons with
whom they have social contacts, each one of the persons
so named may also be asked to do so, and so on. The
researcher may thus get a constellation of associates and
analyze it.

12