6712 4250 Operationalisation(PGDM I) Session II
-
Upload
satyaranjan-sahu -
Category
Documents
-
view
217 -
download
0
Transcript of 6712 4250 Operationalisation(PGDM I) Session II
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
1/38
Operationalization - I
Session II
A researcheridentifies a research problem ora researchable topic with a certainprocedure, specifies objectives, formulatehypotheses with respect to the objectivesand prepares a research design.
Research Design is a Plan, Structure and
Strategy of investigation conceived so as toobtain answers to research questions and tocontrol variance.
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
2/38
The researcher takes all the above points into
account while preparing a Research Design.
Therefore ..
Research Design can differ with respect to
the types of research and various
descriptors. However it encompasses thefollowing steps:
Theory --Hypotheses--Test to validate the
theory or recast the theory--conclusion,
policy implication and recommendation.
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
3/38
An example of the out line of a Research
Design with reference to social science.
A brief background of the study with
reference to the existing literature
( Critical analysis of similar studies and
identification of research questions.) Problem statement.
Objectives of the study (Often referred to as
TOR) Hypotheses formulation with reference to the
objectives.
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
4/38
.Contd
Methodology:Data requirement to test the hypotheses,
Sources of the data and data collection
Requirement of a sample in case of a survey,Tools to use for data analysis and their
rationale
Findings and Analysis
Conclusion, Policy implication and
recommendation & Limitation of the study.
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
5/38
Methodology
Methodology of a study incorporates
Data requirement &Sources
Tools for collection of data Requirement of a sample in case of a
survey
Specification of StatisticalTechniquesto use for data analysis and their
rationale.
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
6/38
Collection of data and sources
Data could be collected through the secondaryor primary source depending on the objectives
of the study and hypotheses to test.
1.Secondary datacould be collected from
published sources or data banks.
Some of the sources are: CSO, ASI,NSS CMIE,
Government Departments, RBI, National Library,
Web sites, etc at the national level and WB,IMF& UN publications at the international levels.
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
7/38
2.Collection of Primary data could be
through a questionnaire orindividual/group
observation or by participatory methods
Primary data could be collected with census or
sample surveys using the above.
Bothquantitative and qualitative data could be
collected.
Data collected through the above tools are
normally cross section data. Time series data
can also be collected from primary sources. Sample surveys are generally used to collect
primary data and conclusion about the
population is arrived at.
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
8/38
Selection of a sample
Census surveys are not feasible always since it
may be extremely difficult, costly and time
consuming.
The purpose ofsampling is to gain as muchinformation as possible about the population by
observing only a small proportion of that
population.
Therefore, the sample chosen should be a
representative of the population i.e. It should
represent the characteristics of the population.
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
9/38
Thus, the need is to identify an appropriate
type of sampling with respect to the purpose
of the study.
This relates to testing relationships in the
sample and generalizing the behaviorof
the observed variables in the sample withrespect to the population with statistical
tests.
To address this aspect we need to knowthe different types of sampling, their
relevance and uses.
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
10/38
Sampling - A few terms used
Element: Unit of population
Sampling units: Elements considered for
sampling in the sample.
Universe: Aggregation of all elements.
E.g. All people living in a country , All
Executives. Population: Specified theoretically with
specific characteristics.
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
11/38
Sampling .contd
A population has a scientific connotation.
All Indian Universities in 2008.
All executives SAIL in 2007-08
All workers in an Industry in 2008.
A specified population is known as a sampling
frame.
A sample is drawn from the population using a
specific sampling techniques with respect to theobjectives of the study.
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
12/38
Sampling .contd
Parameter & Statistics
Parameter: Summary description of a
variable with respect to the population.
Statistics: Summary description of a
variable with respect to a sample.
We test equality of sample statistics withpopulation parameterforgeneralization of
observations .
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
13/38
Types of Sampling-A brief introduction.
1. Simple Random Sampling (SRS)
-Each element in the population has an equal
chance of being selected.
- Sample is drawn by using a lottery method, agenerator, a random number table or a
computer package.
- Use of random number table or computerpackage has wide application in selecting a
sample in social survey when the population
is relatively small
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
14/38
2.Systematic sampling.
In this process a sample of a required size is
selected by selecting the elements of the
population at the beginning at a random start
and following the sampling fraction selectingevery Kth element.
Example: Let us suppose that we have a
population size of 10,000 and we need to select
a sample of 250. Thus we have to select every40th item (10000/250=40) with a random start.
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
15/38
3. Stratified Sampling.
In this process the population is divided in
to sub-populations with the stratification
variables and using simple random
sampling in each stratum a sample isdrawn.
Example: Attitude scaling of consumers of
a particular product. Stratification variablescould be income ,education, occupation
etc.
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
16/38
4. Multistage Cluster Sampling (Sequential
multiphase sampling)
This process divides the population into different
sub-population (clusters) with respect to
geographical, agro-ecological and socio-
economic variables and the process is repeatedmore than once.
In each stage SRS is applied.
This is adopted when the population is large.
Exple: Survey of consumption pattern done by
NSS in India, assessment of productivity of
different crops in a country.
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
17/38
5.Purposive sampling and Accidental
sampling.
Purposive sampling is done with respect to
the specific purpose of the study.
Accidental sampling acquires the
characteristics of SRS if done properly.
Selection of a Sampling Technique depends
On the size of the population, purpose of thestudy, time availability (urgency) and
budget provision for the study.
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
18/38
Instruments for Data collection:Questionnaire Construction
The next step is formulation of a
questionnaire for data collection ( for either
census or a sample survey).
There are several guidelines given by severalauthors about construction of a
questionnaire.
However, the guide lines are subjective
The following are some of the points which a
researcher may take note of while framing a
questionnaire for a survey.
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
19/38
1. Questions and statements
The term 'questionnaire' suggests a set of
questions to be asked to the respondents using
a format.
The researchercan also includestatements/attributes to elicit responses in a
Likert scale to measure attitude of the
respondents.
A Likert Scale may be of a 'seven' or a 'five"
point scale.
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
20/38
Likert Scale Example 1. How important are the
following characteristics for the performances of
the company ?
Characteri
stics
V.Imp Quite Imp
Undecided
Of little
imp
Not imp
Access to
finance
External
financial
service
Sale/Marke
ting skills
Quality of
products
Competitiv
e pricing
Diverse
customer
base
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
21/38
.contd
Alternatively a continuum may also be
used in a Likert Scale.
Two extremes are specified and the rest is
specified with numbers only
1-Strongly disagree & 7-Strongly agree
1.Least Important & 7-Most important
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
22/38
Example 2
Listed below are some of the services that
may influence the choice of a bank.
Please rate the following in a 5 point scale
1- Least Important
5- Most important
(A 7 point scale could be used)
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
23/38
Example 2 (Contd)
Services 1 2 3 4 5
1.
Courteous
service
2.Compete
nce of staff
3.Fast
action on
complaints
5.No of
branches
6.Availabilit
y of ATM
services
7.Financial
strength ofthe bank
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
24/38
Example 3
Likert Scale Contd
In a market research study for a consumer
non - durable such as Premium Soap the
researcher wants to find the importance
attached by the consumer to specifiedattributes .
He may use a Likert Scale to elicit
responses from the consumers andidentify attributes/group of attributes which
are more important.
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
25/38
Example: Premium Soap.
Please rate the following attributes in a scale of 7.
Attribut
es
1 2 3 4 5 6 7
Brand
Price
Freshness
Perfum
e
Size
HygieneLather
Multipur
pose
use
Life
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
26/38
Likert scale Example 4
Rate your manager's communication skills
on the following scale by encircling the
appropriate number.
Very Open Secretive
1 2 3 4 5
Use of both questions and statements
provide flexibility in the design and makes
the questionnaire more interesting.
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
27/38
2. Open-ended and close-ended questions
Open-ended questions: The researcher provides
space for the answer.
Close-ended questions: The respondent is
asked to select answer(s) provided by theresearcher. Two structural requirements for this
type of questions.
The response category should be exhaustive
and it should end with an option 'others'.
The answer category should be mutually
exclusive exceptin case of multiple choice.
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
28/38
3. One should make items/questions clear.
Often the intent /perspectives are clear to
the researcherbutnot clear to the
respondent
Example;
a) What is your income ?.....................
(from all sources? HH Income ? Per year?)
b) The proposed policy change will have a
positive effect on the sale volume. Yes/No
4 Q ti h ld b l t d th
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
29/38
4. Questions should be relevant and the
respondents should be competent to answer
.
Asking on brand preference to a person
who does not know about it is
meaningless.
Asking a respondent in a village:
1.How much do you spend in your children's'
education per year?......................
2. What was your income in the last five
years?.......................................
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
30/38
5.Questionnaire should include short items.
One should avoid double barrel question.
The respondent should be able to read the
items quickly, understand the intent and
select or provide an answer without much
difficulty.
Short, clear and pinpointed questions help
the respondent in understanding the intent
of the questions and the answers will beaccurate to a large extent.
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
31/38
Consider the following question:
The U S should abandon its space program and
spend money on domestic program.
When the researcher is using 'and', he should
check whether he is asking a double-barrelquestion involving two different aspects.
When some people would instantly agree, other
may disagree and a few may not be able to
answer.
Thus, the answer will not be comparable.
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
32/38
6.Avoid negative items:
Inclusion of negative items leads to the
possibilities of misinterpretation.
Often 'not' or 'no' in the question goes
unnoticedby the respondents and they
give the answers which may lead to wrong
conclusion.
E.g. Kashmir Problem is not an internationalissue: Yes/No
High CQPI does not indicate intelligence Yes/No
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
33/38
7. Avoid biased items/ format leading to
biased answer
Questions encouraging/forcing the
respondents to answer in a particular way is a
biased question.
1.Don't you feel that smoking is a bad habit?Yes/No
2. Inadequate response category:
E.g.. Specifying yearly Income category.< 1 Lakh 1-5 Lakh 5-10 Lakh 10-15Lakh >15
The class interval has a bearing on the
population characteristics.
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
34/38
8. Sequence of questions
The questions should be properly ordered to
facilitate the respondents to answer
systematically and with ease.
Properly ordered questions becomeinteresting for the respondent.
Very often, it is better to start a
questionnaire with identification particulars
and demographic features.
Some put these at the end of the
questionnaire.
9 D t j i li d
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
35/38
9.Do not use jargons or specialized
language and avoid questions which
requires calculations.
10. The questions should have
a) A general instruction to the respondents
regarding giving answerorchoices of
codes if codes are used.
b) A set of instructions to the investigators.
c) A draft questionnaire requires pretesting
in the field which gives an opportunity to
identify gaps/mistakes/omissions if any.
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
36/38
Statistical Techniques to Use
After the data are collected, the researcher
tabulates the data by manually of with a
statistical package
Identification of appropriate tools for dataanalysis with respect to the hypotheses.
The analysis facilitates test of hypotheses
and arriving at the conclusion of the
research.
The conclusions help in decision making.
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
37/38
Tools for Data Analysis
Several Statistical/Mathematical
Tools are used for data analysis.
These tools are broadly divided intothree categories.
Univariate tools
Bivariate Tools
Multivariate Tools.
-
7/27/2019 6712 4250 Operationalisation(PGDM I) Session II
38/38
Group Assignment I
Discuss in the group and identify a
topic of research (social or marketing or
any other)
Identify research problem with the help of
literature review.
Formulate hypotheses
Specify data requirement
Prepare a questionnaire to collect data.