Documenti di Didattica
Documenti di Professioni
Documenti di Cultura
Descriptive
Diagnostic
research:
research:
analyse the Objectives portray
characteristics of
frequency with of a particular
which
something research individual,
group, or a
occurs
situation
Hypothesis-testing
research: examine the
hypothesis of a causal
relationship between
two variables
Research Methods vs. Research
methodology
Research methods include all those
techniques/methods that are adopted for
conducting research.
Research methodology is the way in which
research problems are solved systematically. It
is a science of studying how research is
conducted scientifically.
Types of research
Descriptive Versus Analytical
Quantitative Versus Qualitative
Applied Versus Fundamental
Conceptual Versus Empirical
Quantitative Versus Qualitative
research
Quantitative Qualitative
It relates to aspects that can It is concerned with
be quantified or can be qualitative phenomena, or
expressed in terms of more specifically, the
quantity. aspects related to or
Various available statistical involving quality or kind.
and econometric methods are Eg: Motivation Research,
adopted for analysis in such which investigates into the
research. reasons for certain human
behaviour. Most social
science researches are
qualitative.
Features of a good research study.
Examples
HR manager wants to develop HR policies
regarding employees turnover to reduce it.
Marketing manager wants to launch a new
product successfully using advertisement as a
promotional tool
Finance manager needs to invest excessive
money profitably.
Conditions for a research problem to
exist
Z: Uncontrolled
Variables
Y : Environment
OBJECTIVE
ACTION A1 OUTCOME B1
X: Individual or
Organisation P(B1 / X, A1,Y) P (B1 / X, A2, Y).
ACTION A2 OUTCOME B2
Components of a research problem
Thus, the components of a research problem may be summarised as:
i. There should be an individual or a group who have some difficulty or
problem.
ii. There should be some objective(s) to be pursued. A person or an
organization who wants nothing cannot have a problem.
iii. There should be alternative ways of pursuing the objective the
researcher wants to pursue. This implies that there should be more
than one alternative means available to the researcher. This is because
if the researcher has no choice of alternative means, he/she would not
have a problem.
iv. There should be some doubt in the mind of the researcher about
the choice of alternative means. This implies that research should
answer the question relating to the relative efficiency or suitability of
the possible alternatives.
v. There should be a context to which the difficulty relates.
Illustration
Let us suppose the research problem is
Why is productivity in Japan so much higher than
in India?
Flaws: What sort of productivity? Which industry?
Which time period?
What factors were responsible for the high labor
productivity of Japans manufacturing industries
during the decade 1971-1980 relative to Indias
manufacturing industries?
Flaws: To what extent did it exceed that of Indias?
Illustration
To what extent did labor productivity in 1971-
1980 in Japan exceed that of India in respect
of 15 selected manufacturing Industries?
What factors were responsible for the
productivity differentials between the two
countries?
Exercise 1
Problem situation: In a District K of a State L a report showed
that in the first month there were 500 children under one year old
who started immunization, but at the end of the year it was found
out that there were only 25 children who completed their
vaccination.
Discrepancy: All the 500 children at district K should have
completed their vaccination but only 5% out of those who started
vaccination have completed.
Problem (research) question: why only 5% of the children
completed their vaccination?
Definite answer: Out of the 1 hospital, 2 health centers and 10
health stations found in the district only 2 health stations were
functioning, the rest were closed due to insecurity in the area.
In the above example, assuming that all the given facts are true,
there is no need of undertaking a research, since definite answer
is obtained to the problem situation.
Exercise 2
Problem situation: In district Z (population 150,000) there are 2
health centres, 1 hospital and 15 health stations and all of them
function smoothly. However, at the end of the year it was found that
the EPI coverage was only 25%.
Discrepancy: Although district Z had 100% availability of health
services and at least 80% of the children should have had full
vaccinations the EPI coverage was only 25% as seen above.
Problem question: What factors influence the low EPI coverage in
district Z?
Possible answers:
Mothers might have problems for not attending in the EPI sessions.
The programmes might not have been integrated; hence children
might have missed opportunities in getting immunization.
The follow up of defaulting children might not be effective and
other reasons.
Thus, the above problem situation is researchable.
Ethics
People first, research next.
Participants are informed before the experiment.
Debriefing of the participants.
Participants are allowed to withdraw in the
middle of the research.
In case of undesirable incidents it is the duty of
the researcher to make the participant feel
comfortable.
Data collected should be kept confidential.
(2) Extensive literature survey
Your literature search should establish what
previous researches have been carried out in the
subject area.
How much is known?
What is not known?
What should be done based on what is
lacking?
Review of literature is a list of relevant books
and other sources, each followed by a
description and comment on its relevance.
Sources for literature review
Broadly speaking, there are three kinds of
sources that you should consult:
1. Introductory material;
2. Journal articles and
3. Books.
Use of literature review
It prevents you from duplicating work that has been done before.
It increases your knowledge on the problem you want to study and this may assist
you in refining your "statement of the problem".
It gives you confidence why your particular research project is needed.
To be familiar with different research methods
(3) Developing hypothesis
A hypothesis is a prediction of a relationship between
one or more variables and the problem under study.
A research hypothesis is quite often a predictive
statement, which is capable of being tested using
scientific methods that involve an independent and
some dependent variables.
Experimental Non-experimental
Experimental Research Designs
Professor R.A. Fishers name is associated with
experimental designs.
Professor Fisher found that by dividing
agricultural fields or plots into different blocks
and then by conducting experiments in each
of these blocks, whatever information is
collected and inferences drawn from them,
happens to be more reliable.
BASIC PRINCIPLES OF EXPERIMENTAL
DESIGNS
Principle of Replication, the experiment should be repeated
more than once. Thus, each treatment is applied in many
experimental units instead of one.
The Principle of Randomization provides protection, when we
conduct an experiment, against the effect of extraneous
factors by randomization.
Principle of Local Control: Under it the extraneous factor, the
known source of variability, is made to vary deliberately over
as wide a range as necessary and this needs to be done in
such a way that the variability it causes can be measured and
hence eliminated from the experimental error.
Eg: Effect of two varieties of rice in a piece of land.
Extraneous factor is soil fertility.
Types of experimental designs
Informal Formal
For example, the statistics collected Later when the same data are used
by the Government of India relating by a researcher for his study of a
to the population is primary data for particular problem, then the same
the Government of India since it has data become the secondary data for
been collected for the first time. the researcher.
How to select primary or secondary
data?
Data
Primary Secondary
Census method
time taking, it requires more labour Published sources Eg: RBI
and it is very expensive. 100%
accurate
Leading
Shut questions
questions
Simple alternate framed into two
questions questions-
Yes or No alternatives.
(i) which car do you use?
Multiple choice questions
(ii) why do you prefer it?
Do you smoke?
It gives smooth ride [ ]
(a) Yes regularly [ ] (b) No It gives more mileage [ ]
never [ ]
It is cheaper [ ]
(c) Occasionally [ ] (d)
It is maintenance free [ ]
Seldom [ ]
The Suitability Of Data
Adequacy Of Data:
Reliability Of Data: