SYLLABUS

Introduction to Business Research & uses of software: Types of

Research, Business Research, Business Research Process, Uses of
Software in Data Preparation and Analysis, Business Research Process
Design
Research Design Formulation: Measurement and Scaling,
Questionnaire Design and its Process, Sample Design: Types of
Sampling, Sample size, sampling error.
Sources and Data Collection: Types of data, Secondary data
sources, Primary Data Collection: Survey and Observation, semi-
structured interview, in-depth interview and questionnaire,
Data Analysis and Presentation: Hypothesis testing and errors,
Application of Z-test, t-test, F-test and Chi Square-test and Analysis
of Variance (ANOVA), Correlation and Simple Regression
Analysis, Introduction to Bi-variate & Multi-variate analyses
Result Presentation: Research report writing and presentation of
results
Research?
Research
Ø Research is all about finding something, the absence of which may
distort our ability to take informed decisions (Nwokah et al., 2009).

Ø The ability to take an informed decision is generated through a

systematic study that is conducted through various interrelated
stages.

Ø All the steps in a research are interrelated and no independent

activity is launched without considering the decisions on the previous
stages.
What Business Researchers do?
Ø Business researchers systematically collect, compile,
analyze, and interpret data to provide quality information
based on which a decision maker will be able to take a decision in
an optimum manner.
 ØBusiness research method is a systematic and
scientific procedure of data collection,
compilation, analysis, interpretation, and
implication pertaining to any business problem.
Defining
Business ØBusiness research is defined as the systematic
Research and objective process of gathering, recording,
and analyzing data for aid in making business
decisions (Zikmund, 2007).

ØCooper and Schindler (2009) define business

research as a systematic enquiry that provides
information to guide managerial decisions.
Difference Between Basic and
Applied Research

Ø Basic research is generally not related to a specific problem

and its findings cannot be immediately applied.
Ø Applied research directly addresses the problem at hand.
Applied research is launched by the firm, agency, or individual facing a
specific problem.
Interrelated Steps in Business Research

1 2 3 4 5

Problem or Diagnosing Executing Implement Evaluate the

opportunity the problem business presented effectiveness
identification or research to solutions of decision
opportunity explore the making
solutions
Types of
Research
 Theoretical / Fundamental/ Pure/ Basic

● Developes a theory in any discipline of physical or social

sciences.
● Driven by inquisitiveness or curiosity of researcher on
behavior of phenomenon.
● Objective - to extend (enhance) the existing knowledge; not to
create or invent something.
● Researcher may not have the intention of using the outcome of
research immediately.
● Could be used in future.
 Theoretical / Fundamental/ Pure/ Basic

● Results in establishment of theories.

● These are examined by society which leads to restatement of
existing theory.
● Therefore, aims at building, re-examining, restating theories.
● Example - laws of newton, how did the universe begin, law of
demand, law of price, research related to theories of marketing,
finance, human resource, etc.
● Several theories on existence of earth.
 Theoretical / Fundamental/ Pure/ Basic

● Can also be termed as disciplinary research because the basic

objective is to develop theories in any discipline and to improve
that discipline.
● Another ex. Changing motivational factors of Indian buyers after
liberalization.
● Intention to use digital payment after demonitization.
Applied Research
● Problem/ issue based.
● Launched by a firm/ agency or individual facing a
specific problem.
● Findings presented to decision maker who takes the
decision to address the problem.
● Example - why are employees leaving an
organization?
● Why did Nokia fail?
● Why are sales of company decreasing?
● Cure of a specific illness? Example Ebola Virus?
Difference Between
Fundamental and Applied
Research?????
Difference Between Fundamental and Applied
Research

● In terms of application of findings.

● In Applied research, findings are applied immediately,
whereas in basic research, findings may not be applied
immediately.
● Applied research is problem based, basic research is
done for the sake of knowledge.
Difference Between Fundamental and Applied
Research

● They are not opposite of each other. Just two ends of a

continuum.
● In some cases they might merge or lead to other.
● Ex. Studies in Mathematics leading to development of
computer/ laptop/ smartphones.
● Merger of 2 organization on employee morale and
turnover intention.
Exploratory Research

● As the name indicates, exploratory research is mainly used to

explore the insight of the general research problem.
● Unstructured, flexible, freedom to researcher.
● Sample used is mostly small and mostly determined on the
basis of convenience of researcher.
● Not conclusive.
● Require further exploratory or conclusive research.
Exploratory Research

This is used for the following purposes:

A. Obtaining Background Information
B. Research Problem Formulation or Defining it More Precisely
C. Identifying and Defining the Key Research Variables
D. Developing Hypotheses
Conclusive Research

● Tests and authenticates the propositions revealed

by exploratory research.
● Tests formulated hypothesis and specified
relationships.
● Structured and definitive.
● Time frame of study and respondent selection is
more formal and representative.
 Difference between
Exploratory and Conclusive
Research????
Exploratory Research Conclusive Research
● Loosely Structured ● Well structured and
● Flexible and systematic
investigative ● Formal and
● Does not involve testing definitive
of hypothesis ● Test of hypothesis
Types of Conclusive
Research
● Descriptive
● Causal
Descriptive Research

● Descriptive research is research used to “describe” a

situation, subject, behavior, or phenomenon.
● It answers who, what, where, when and how type of
questions. Not why.
● Description research is used to observe and describe a
research subject or problem without influencing or
manipulating the variables in any way.
Descriptive Research

● Examples,
1. Finding the most frequent disease that affects the
children of a town.
2. Descriptive research on Consumption pattern of a
product revealed 80% are government employees, 10%
are business men, and remaining are scattered. 70%
customers are men and 30% are women etc.
Descriptive Research

● Examples,
3. Market researchers may want to observe the habits of
consumers.
4. A company may be wanting to evaluate the morale of the
staff.
5. Research on whether students are more likely to access
online textbooks or to use printed copies.
Descriptive Research

● Examples,
6. Research on characteristics of customers who buy normal
petrol and those who buy premium petrol.
7. What is the level of involvement of middle level vs. senior
level managers in company’s stock related decisions?
 Causal Research

● The emphasis is on establishing cause and effect relationship.

● Effect of one variable on other. Establishes Causality. Why of a
phenomenon.
● Examples
1. Effect of stress on smoking habits. Age on self esteem, Weight
on self esteem.
2. Effect of advertisement campaign on product sales.
3. Effect of presence and helpfulness of sales people on sales.
Concept of
Causality
Cross Sectional vs Longitudinal Research

ØCross sectional research design involves the collection of

information from a sample of a population at only one point
of time.

Ø Involves large samples from the population; hence,

sometimes referred as “sample surveys.”

ØLongitudinal study involves survey of the same population

over a period of time.
Difference between Cross Sectional vs
Longitudinal Research???

Ø In a longitudinal study, the sample remains the same

over a period of time. In a cross-sectional design, a
representative sample taken from the population is studied
at only one point of time.
Cross Sectional vs Longitudinal Research

Example - Let’s say we want to investigate the relationship

between daily walking and cholesterol levels in the body.

Do we want to compare cholesterol levels among different

populations of walkers and non-walkers at the same point in
time? Or, do we want to measure cholesterol levels in a
single population of daily walkers over an extended period of
time?
The defining feature of a cross-sectional study is that it can
compare different population groups at a single point in
time.

However, cross-sectional studies may not provide definite

information about cause-and-effect relationships.

Longitudinal study is more likely to suggest cause-and-

effect relationships than a cross-sectional study.
 Experimental Research

Experimental research designs are the primary approach used to

investigate causal (cause/effect) relationships and to study the
relationship between one variable and another.

In these designs, one variable is manipulated to see if it has an

effect on the other variable.
 Key Terminology
Independent Variable – This is the variable that will be
manipulated, the “cause” or treatment variable.

Dependent Variable – This variable is the “effect” or

outcome of manipulating the independent variable.

Experimental Group – The group that receives the

treatment being investigated.

Control Group – The group that remains the same in

order to have something to compare the experimental
group against.
Example - Effect of a drug
on Blood Sugar levels.
Quantitative vs
Qualitative
Research
Quantitative Research

● Based upon quantitative data.

● Suitable statistical methods are used to arrive at
conclusion.
● Example relationship between advertising expenditure and
sales revenue.
● Price and demand.
● Share price and earning per share.
Qualitative Research

● Based upon qualitative data.

● Example shopping behavior, human behavior, culture,
eating habits., factors that lead to motivation etc.
Revision
Time
Fundamental research is same as
(a)Theoretical research
(b)Laboratory experiments
(c)Survey research
(d)None of the above
Disciplinary research is
otherwise known as
(a)Pure research
(b)Fundamental research
(c)Basic research
(d)All of the above
The basis of applied research is
(a) Pure or fundamental research
(b)Qualitative research
(c) Field experiments
(d)None of the above
 Identify?
There has been a decline in the market share of a company
producing consumer non-durables. It observes various
competitors in the market for its product. The management
wants to intervene in the market by influencing the perception
of the consumers. It offers various freebies to the buyers,
advertises about is products in the media and uses hoardings in
places where it can attract the consumer’s attention. After, one
year of such intervention, he hires a consultant to study the
impact. Which type of research is conducted here?
 Identify?
A motorcycle manufacturer has found that there
have been various complaints on a specific part of
the motorcycle. To address this, it asks the
production manager to examine and report the
defect, if any. What type of research will be this?
Variable??
Variable - a symbol of an event, act, charateritic, trait that varies
across entities and time.
- Varies across entities
- Varies across time.

Ex. income of an individual for few years

Or income of few individual in 2018.

Other ex - profit, expenditure, sales, etc are all variables.

Types of Variables
Qualitative vs Quantitative:

Quantitative: Any variable that can be counted directly i.e. it has

direct ways of measurement and can take any value.
Ex. income, expenditure, tax revenue, sales volume and profit
etc.

Qualitative: Any variable that represents a quality, an attribute or

property. These are not directly measured but may have indirect
ways of measurement. Number may be assigned to qualitative
variables for data analysis but these are still qualitative.
Ex - gender, brand loyalty, intelligence, economic status etc.
Dichotomous and Polytomous

Dichotomous / Binary: A variable that can take only two values.

Ex- gender (male or female),
loyalty (loyal or not loyal),
Employment status (employed or unemployed)
Marital status (married or un married)
Exam result (pass/fail)
Entrance result (admitted/ not admitted)
Polytomous/ Polychotomous Variable: A variable that can take
more than two values.
Ex. income, Expenditure, profit, sales revenue.
Or say level of education
Caste, religion.

Types - Ordered Polytomous : Have a particular order. Ex. level

of education

Unordered Polytomous: They don’t have an implied order. Ex.

Religion.
Discrete and Continuous:

Discrete: A variable that can take only a certain number of values

and can fit into categories are said to be discrete.

Ex. an automotive variable where Chevrolet is assigned 5 and

Honda is assigned 6 will not have any option of 5.5.

Other ex - number of persons in a family, number of casr in

parking, number of coins in a purse.
Discrete and Continuous:

Continuous: can take values within a given range or in some

cases, an infinite set. Infinite number of possible values.
Ex - weight, height, temperature, income, price etc.

A continuous variable does not have to be every possible values (

i.e minus infinity to plus infinity). It can be continuous between
two numbers like 1 and 2.

Here 1 and 2 are discrete. And 1.01, 1.001, 1.0001 are continuous.
Dependent and Independent:

Researchers are mostly interested in relationships among

variables.

IV: This variable is manipulated by the researcher. Manipulation

causes an effect on dependent variable.

DV: This variable is monitored, measured and is expected to be

affected by the manipulation of IV.

Ex - you want to know how calorie intake affects weight.

Other Names
Dependent
Independent
Predictor
Criterion
Cause
Effect
Stimulus
Response
Input
Output
Antecedent
Consequence
Manipulated
Measurement and Scaling
Measurement:
Assigning numbers to observations in compliance with a set of
rules.

Scaling:
The process used to measure.

3 part process:
1. There should be observable events, objects or properties
that are to be measured.
2. Developing mapping rules - scheme of assigning numbers.
3. Applying mapping rules to each event.
Levels of Measurement/ Types of Scales

1. Nominal
2. Ordinal
3. Interval
4. Ratio
ØNominal Scale: When data are labels or names used to
identify the attribute of an element, the nominal scale is
used.
ØOrdinal Scale: In addition to nominal level data
capacities, ordinal scale can be used to rank or order
objects.
ØInterval Scale: In interval level measurement, the
difference between two consecutive numbers is meaningful.
ØRatio Scale: Ratio level measurements possess all the
properties of interval data with meaningful ratio of two
values.
A comparison between the four levels of data measurement in terms
of usage potential
Test your understanding
Which of the following is an example on
nominal data?
A. Attractiveness
B. Gender
C. Height
D. Temperature
Which of the following statements best
relate to nominal data?
A. Category membership
B. Data is ranked along a continuum
C. Equal intervals and a true zero point
D. Numbers assigned serve only as labels
In context, which of the following is an example of
interval data?
a. Sully is 4'6"; Mike is 2'3"
b. Sully is TALL; Mike is SMALL
c. Sully is TALLEST; Mike is SECOND TALLEST
d. Sully wears SIZE 12; Mike wears SIZE 4
Which of the following statements best
relate to interval data?
a. Equal intervals and a true zero point
b. Intervals between ranks are not equal
c. Intervals between successive values
are equal
d. No true zero point
In context, which of the following is an
example of ordinal data?
a. Sully is 4'6"; Mike is 2'3"
b. Sully is TALL; Mike is SMALL
c. Sully is TALLEST; Mike is SECOND
TALLEST
d. Sully wears SIZE 12; Mike wears SIZE
4
In context, which of the following is an
example of ratio data?
a. Sully is 4'6"; Mike is 2'3"
b. Sully is TALL; Mike is SMALL
c. Sully is TALLEST; Mike is SECOND
TALLEST
d. Sully wears SIZE 12; Mike wears SIZE
4
Which of the following statements best relate to
ordinal data?
a. Data is ranked along a continuum
b. Intervals between ranks are not equal
c. intervals between successive values are equal
d. There is no true zero point
Which of the following is an example on interval
data?
a. Attractiveness
b. Gender
c. Height
d. Temperature
In context, which of the following is an example of
nominal data?
a. Sully is 4'6"; Mike is 2'3"
b. Sully is TALL; Mike is SMALL
c. Sully is TALLEST; Mike is SECOND TALLEST
d. Sully wears SIZE 12; Mike wears SIZE 4
The order in which participants complete a task is
an example of what level of measurement?

Ordinal
Nominal
Ratio
Interval
What level of measurement would be used if
participants were asked to choose their favourite
picture from a set of six?

Ordinal
Nominal
Ratio
Interval
What is the difference between data measured on
an interval scale and data measured on a ratio
scale?
A. A ratio scale has a true zero point, so zero on the scale
corresponds to zero of the concept being measured.
B. An interval scale has a true zero point, so zero on the scale
corresponds to zero of the concept being measured.
C. A ratio scale has equal intervals between the points on the
scale, whereas an interval scale does not.
D. A ratio scale puts scores into categories, while an interval
scale measures on a continuous scale.
Scaling
Techniques
 Scaling Techniques (on
the basis of comparison)

Non-
Comparative Comparative
Scales Scales
 Comparative Scales

● There is a direct comparison of stimulus object.

● Ex - Respondent might be asked directly about his preference between
the ink pen and gel pen.
● Comparative data can only be interpreted in relative terms and hence
possess the ordinal or rank-order properties.
● Comparative scaling is also called as non-metric scaling.
 Non-Comparative Scales

● Each object is scaled independently of the other objects in

the stimulus set under study
● Example, a respondent may be asked to rate their preference
for the gel pen on a preference scale (1 = not at all preferred,
6 = greatly preferred)
● The resulting data are assumed to be an interval and ratio
scaled.
● Also called as monadic or metric scale
Scaling Techniques (on the basis of number of items used)
1. Single-Item Scales

● As clear from the name, the single-item scales measure only

one item as a construct.
● Some of the commonly used single-item scales in the field of
business research are multiple choice scales, forced-ranking
scales, paired-comparison scales, constant-sum scales, direct
quantification scales, and Q-sort scales.
1. (a) Multiple-Choice Scale

● The researcher poses a single question with multiple

response alternatives.
● For a mere quantification reason, a researcher assigns 1 to
the first response, 2 to the second response, and so on.
● Results in generating the nominal data.
Examples of Multiple-Choice Scale
1. (b) Forced-Choice Scale

● The respondents rank different objects simultaneously

from a list of objects presented to them.

● Results in generating ordinal-level data.

● Also referred as rank order scaling technique.

Examples of Forced-Choice Scale
1(c) Paired-Comparison Technique

● The respondent is shown two objects (pair of objects) at the

same time and is asked to select one according to the defined
criterion. The resulting data are ordinal in nature.
● Data so obtained can be analyzed in either of the ways. First,
the researcher can compute the percentage of respondents
who prefer one object over another.
● Sometimes, a researcher uses the “principle of transitivity”
Example of Paired-Comparison Scale
1(d) Constant-Sum Scales

● The respondents allocate points to more than one stimulus

objects or object attributes or object properties, such that the
total remains a constant sum of usually 10 or 100.

● This scaling technique generates the ratio-level data.

Example of Constant-Sum Scale
1(e) Direct Quantification Scale

● Directly ask a question related to some characteristics of interest.

● Simplest form of obtaining information

● Resulting in ratio-scaled data.

● Examples -
1(f) Q-Sort Scaling

● The respondents are asked to sort the presented objects into

piles based on similarity according to a specified criterion such
as preference, attitude, perception, etc.
● For example, suppose the respondents are given 100
motivational statements on individual cards and are asked to
place these in 11 piles, ranging from the “most agreed with”
to the “least agreed with”. Generally, the most agreed
statement is placed on the top while the least agreed statement
at the bottom.
1(f) Q-Sort Scaling

● Ideally, the objects to be sorted shall not be less than 60 and

not more than 140. While, the range between 60 to 90 is
considered as the most reasonable range.
Multi-Item Scales
- Likert
- Semantic
- Stapel
- Numerical
2. Multi Item Scaling Technique

A multi-item scale is designed to measure the respondent’s attitude towards

more than one attribute related to the stimulus object. It is a rating scale
comprising of multiple items, where each item is a single question or a
statement that needs to be evaluated.

Ex- if to measure loyalty a researcher asks a question “how likely are you
to recommend to a friend” - Single item scale.

But, if various questions are asked related to various attributes of loyalty

then it is multi item scale.
2(a) Likert Scale

● The Likert Scale was named after its developer, Rensis Likert.
● Each item response has five rating categories, “strongly disagree” to
“strongly agree” as two extremes with “disagree,” “neither agree nor
disagree,” and “agree” in the middle of the scale. Typically, a 1- to 5-
point rating scale is used, but few researchers also use another set of
numbers such as −2, −1, 0, +1, and +2.
● The data obtained from the Likert Scale are typically treated as the
interval.
● Time-consuming and requires much more time.
Example of Likert scale
2(b) Semantic Differential Scales

● The semantic differential scale consists of a series of bipolar adjectival

words or phrases placed on the two extreme points of the scale.

● Scale could be on 5 points or 7 points.

● The respondent will place a mark anywhere between the two extreme
adjectives, representing his attitude towards the object.
Example of semantic differential scale
Another Example

The respondent might be asked to rate the following five attributes of

shoppers stop by choosing a position on a scale between the adjectives that
best describe what really the shoppers stop means to him.
● Good semantic differential scales keep some negative
adjectives and some positive adjectives on the left side of the
scale to tackle the problem of the halo effect.

● Halo Effect????

● The tendency for an impression created in one area to

influence opinion in another area.
2(c) Stapel Scales

● Stapel Scale is a unipolar (one adjective) rating scale designed to

measure the respondent’s attitude towards the object or event. The
scale comprises of 10 categories ranging from –5 to +5.
● The scale is usually constructed vertically with a single adjective in the
middle of the range of values (-5 to +5).
● The respondent is asked to select the appropriate numerical response
category that best describes the extent to which the adjective related to
the object is accurate or inaccurate.
● The higher the positive score selected by the respondent, the more
accurate the adjective describes the object and vice versa.
Example of staple scale
Another Example:

The respondent is asked to rank the quality of food, and crew member
service of an airline on a scale ranging from -5 to +5:

From this example,

the airline is evaluated
as having a high food
quality but somewhat
poor cabin crew service.
2(d) Numerical Scales

● Numerical scales provide equal intervals separated by numbers, as

scale points to the respondents.

● These scales are generally 5- point but may have 7 or 10 points.

● Verbal anchor serve as labels for extreme points.

● Interval data.
Example of Numerical scale
3. Continuous Rating Scales

● In a continuous rating scale, the respondents rate the object by

placing a mark on a continuum to indicate their attitude. In this scale,
the two ends of continuum represent the two extremes of the measuring
phenomenon.
● This scale is also referred as a graphing rating scale and allows a
respondent to select his or her own rating point instead of the rating
points predefined by the researcher.
● Respondent is not restricted to select from the values as previously set
by the researcher.
Example of Continuous scale
Few Examples………..
You receive the results of a paired-comparison preference test of
four soft drinks from a sample of 200 persons. The results are as
follows: Koak Zip Pabze
Mr. Peepers
Koak -- 50* 115
35
Zip 150 -- 160
70
Pabze 85 40 -
- 45
Mr. Peepers 165 130 155
—
Assume you are Menu Foods and you planned a major research
study just prior to the largest pet food recall in our history. You
plan to proceed with the study and feel you must add one or more
questions to measure the consumer’s confidence that your firm
will be able to recover. Draft a scale for each of the following
types that will measure that confidence.
a Constant-sum scale.
b Likert-type summated scale.
c Semantic differential scale.
d Stapel scale.
e Forced ranking scale.
Test your
Understanding
Indicate the type of scale (nominal, ordinal, interval or ratio)
that is being used in the following...

● How large is the market size for shampoos?

Indicate the type of scale (nominal, ordinal, interval or
ratio) that is being used in the following...

● In which of the following functional areas of

management do you wish to specialize in second
year?
(a)Marketing
(b)Finance
(c)HR
(d)IT
Indicate the type of scale (nominal, ordinal, interval or ratio)
that is being used in the following...

● State the order of your preference for the following

colors.
(a)Grey
(b)White
(c)Blue
(d)Green
(e)Black
Indicate the type of scale (nominal, ordinal, interval or
ratio) that is being used in the following...

● Is the research methods course difficult to

understand?
(A)Yes
(B)No
Indicate the type of scale (nominal, ordinal, interval or ratio)
that is being used in the following...

● How do you rate the quality of food at the Golden

Dragon restaurant?
1= Very poor
2= poor
3= neither poor nor good
4= good
5= very good
1. Construct a 10 item likert scale to measure the perception
of bank customers towards the concept of Internet
Banking.

2. Construct a 10 item semantic differential scale (7 points)

to measure the image of coffee joint - cafe coffee day.

3. Design a 5-item likert scale to measure the opinion of

the general public for what measures should be taken to ensure
the safety of women in the Indian cities.
Reliability and
Validity of
Measurement
Imagine that you have been dieting for a month. Your
clothes seem to be fitting more loosely, and several friends
have asked if you have lost weight. If at this point your
bathroom scale indicated that you had lost 10 pounds, this
would make sense and you would continue to use the scale.
But if it indicated that you had gained 10 pounds, what
would you conclude?

These is related to issue of reliability and validity.

Reliability

● Reliability refers to the consistency of a measure.

● Reliability is the tendency of a respondent to respond in the same or in a

similar manner to an identical or a near identical question.

● A measure is said to be reliable when it elicits the same response from the
same person when the measuring instrument is administered to that person
successively in similar or almost similar circumstances.
Reliability

● If a measuring instrument is not reliable, it will generate different responses

from the respondents who have the same feeling about the phenomenon.

● Three types of consistency: over time (test-retest reliability), across items

(internal consistency), and across different researchers (inter-rater
reliability).
Test-Retest Reliability
When researchers measure a construct that they assume to be consistent
across time, then the scores they obtain should also be consistent across
time. Test-retest reliability is the extent to which this is actually the case.
For example, intelligence is generally thought to be consistent across
time. A person who is highly intelligent today will be highly intelligent
next week. This means that any good measure of intelligence should
produce roughly the same scores for this individual next week as it does
today. Clearly, a measure that produces highly inconsistent scores over
time cannot be a very good measure of a construct that is supposed to be
consistent.
Procedure for Test-Retest Reliability

● Assessing test-retest reliability requires using the measure on a group

of people at one time, using it again on the same group of people at a
later time, and then looking at test-retest correlation between the two
sets of scores. This is typically done by graphing the data in a
scatterplot and computing Pearson’s r.

● In general, a test-retest correlation of +.80 or greater is considered to

indicate good reliability.
Test-Retest Reliability

● High test-retest correlations make sense when the construct being

measured is assumed to be consistent over time, which is the case for
intelligence, self-esteem etc.
● But other constructs are not assumed to be stable over time. For
example - mood. So a measure of mood that produced a low test-
retest correlation over a period of a month would not be a cause for
concern.
Limitation of Test-Retest Reliability
● What should be the ideal time interval between two responses.?

● There is a possibility that respondent will answer the same question in

the same way because the first response memory is still in his mind.

● There is a great possibility that some external environment may alter

the respondent's view and therefore, his her second answer will be
different from first answer.
Internal Consistency Reliability

● Consistency of people’s responses across the items on a multiple-

item measure. In general, all the items on such measures are supposed
to reflect the same underlying construct, so people’s scores on those
items should be correlated with each other.

● If people’s responses to the different items are not correlated with

each other, then it would no longer make sense to claim that they are
all measuring the same underlying construct.
Example

You want to find out how satisfied your customers are with the level of
customer service they receive at your call center. You send out a survey with
three questions designed to measure overall satisfaction. Choices for each
question are: Strongly agree/Agree/Neutral/Disagree/Strongly disagree.

● I was satisfied with my experience.

● I will probably recommend your company to others.
● If I write an online review, it would be positive.

If the survey has good internal consistency, respondents should answer the
same for each question, i.e. three “agrees” or three “strongly disagrees.” If
different answers are given, this is a sign that your questions are poorly worded
and are not reliably measuring customer satisfaction.
Procedure for Internal Consistency Reliability

● An approach to measure is through split-half correlation.

● This involves splitting the items into two sets, such as the first and
second halves of the items or the even- and odd-numbered items. Then
a score is computed for each set of items, and the relationship between
the two sets of scores is examined.
● A split-half correlation of +.80 or greater is generally considered good
internal consistency.
● Most common measure of internal consistency used by researchers in
psychology is a statistic called Cronbach’s α (alpha).
● Varies from 0 to 1.
● Value less than 0.6 is considered to be unsatisfactory.
Inter Rater Reliability

● Inter-rater reliability is the extent to which different observers are

consistent in their judgments.

● For example, if you were interested in measuring university students’

social skills, you could make video recordings of them as they interacted
with another student whom they are meeting for the first time. Then you
could have two or more observers watch the videos and rate each
student’s level of social skills. To the extent that each participant does in
fact have some level of social skills that can be detected by an attentive
observer, different observers’ ratings should be highly correlated with
each other.
Procedure for Inter Rater Reliability

● Inter-rater reliability is the level of agreement between raters or judges.

● If everyone agrees, IRR is 1 (or 100%) and if everyone disagrees, IRR is

0 (0%). Several methods exist for calculating IRR, from the simple (e.g.
percent agreement) to the more complex (e.g. Cohen’s Kappa).
● The field you are working in will determine the acceptable agreement
level. If it’s a sports competition, you might accept a 60% rater
agreement to decide a winner. However, if you’re looking at data from
cancer specialists deciding on a course of treatment, you’ll want a much
higher agreement — above 90%. In general, above 75% is considered
acceptable for most fields.
Validity

● It means that a test or instrument is accurately measuring what it’s

supposed to.

● Is the extent to which the scores from a measure represent the variable
they are intended to.

● A measure can be extremely reliable but have no validity whatsoever.

An absurd Example:

● Imagine someone who believes that

● people’s index finger length reflects their self-esteem and
● therefore tries to measure self-esteem by holding a ruler up to people’s
index fingers.
● Although this measure would have extremely good test-retest
reliability, it would have absolutely no validity.
● The fact that one person’s index finger is a centimetre longer than
another’s would indicate nothing about which one had higher self-
esteem.
 Types - Face Validity

● Face validity is the extent to which a measurement method appears “on

its face” to measure the construct of interest.
For ex-
● A self esteem questionnaire should include items about:
whether they see themselves as a person of worth and whether they
think they have good qualities.
● The finger-length method of measuring self-esteem, on the other hand,
seems to have nothing to do with self-esteem and therefore has poor
face validity.
Content Validity

● Extent to which a measure “covers” the construct of interest.

● For example:
if a researcher conceptually defines test anxiety as involving both
nervous feelings and negative thoughts, then his measure of test
anxiety should include items about both nervous feelings and negative
thoughts.
Content Validity

● Similarly, attitudes are usually defined as involving thoughts,

feelings, and actions toward something.

● Therefore, a person has a positive attitude toward exercise to the

extent that he or she thinks positive thoughts about exercising, feels
good about exercising, and actually exercises.

● To have good content validity, a measure of people’s attitudes toward

exercise would have to reflect all three of these aspects.
 Criterion Validity

● The extent to which people’s scores on a measure are correlated with

other variables (known as criteria) that one would expect them to be
correlated with.

● For example, people’s scores on a new measure of test anxiety should be

negatively correlated with their performance on an important school
exam.
Sampling
Sample and Sampling

● A researcher generally takes a small portion of the

population for study, which is referred to as sample.
● The process of selecting a sample from the population is
called sampling.
 Sampling Concepts

● Population:

Any group of people or objects that form the subject of the

study, about whom the inference has to be made.

Example:

- if we are interested in understanding the perception of MBA

students about business education and there are 200 MBA
students in a business school then population size would be
200.
 Sampling Concepts

- If a TV manufacturing company produces 150 TVs per week

and we are interested in estimating the proportion of
defective TVs produced per week then population size would
be???
- If there are 1000 engineers in an organization out of which
350 are mechanical engineers. If we are interested in
examining the proportion of mechanical engineers who
intend to leave the organization then population size would
be????
 Sampling Concepts

● Element:

A single member/an individual unit of the population.

Ex.
- out of 350 mechanical engineers, each of them would form an
element/unit of the population.
- Out of 200 MBA students, each student will be an element of
the population.
 Sampling Concepts

● Sampling Frame:

- List that possesses the information about the subjects.

- A researcher takes a sample from the sampling frame.

Ex-
- The number of students registered with the university.
- The attendance sheet of a particular class.
- Payroll of an organization.
 Sampling Concepts

● Sampling Frame:

- When population size is very large, it becomes virtually

impossible to form a sampling frame.

- Ex- there is a large number of consumers of soft drinks,

therefore, it becomes difficult to form a sampling frame.
 Sampling Concepts

● Sample:

- It is subset of the population.

- Comprises only some elements of the population.
Ex-
- If out of 350 mechanical engineers, 30 are surveyed regarding
their intention to leave the organization in the next six
months, these 30 would constitute the sample.
 Sampling Concepts

● Sampling Unit:

Every single member of the sample is called sampling unit.

Ex-
- Out of 30 mechanical engineers chosen as sample, every
single engineer is a sampling unit.
- Out of 50 MBA students chosen as sample, each student is a
sampling unit.
 Sampling Concepts

● Sampling:

- A process of selecting an adequate number of elements from

the population.

Types-

● Probability sampling.
● Non- Probability Sampling
 Sampling Concepts

● Census (Complete Enumeration):

Examination of each and every element of the population.

 Sampling Concepts

● Census (Complete Enumeration):

Examination of each and every element of the population.

Why is Sampling Essential?

● Sampling saves time and cost.

Ex- if we are interested in knowing monthly average household

expenditure on food items of people of delhi. Population is approx
1.2 crore. If we assume that there are five members per household,
then population comprises 24 lakh households. Collecting data from
these 24 lakh households would be time consuming and expensive.
Why is Sampling Essential?

● Sampling minimizes destruction when research process is

destructive in nature. Sampling is the only option.

Ex-
- to estimate the average life of bulbs, they have to be burnt out
completely. So complete enumeration can not be done.
- Blood sample.
Why is Sampling Essential?

● There are situations when decision maker may not have too
much time to wait till all the information is available.
Probability
Sampling /
Random
Sampling
Methods
Probability/ Random Sampling

In random sampling, each unit of the population has the equal probability
(chance) of being selected as part of the sample.

Non-probability/ Non-Random Sampling

In non-random sampling, members of the sample are not selected by

chance. Some other factors like familiarity of the researcher with the subject,
convenience, etc. are the basis of selection.
 Random Sampling Methods

1. Simple Random Sampling:

● Each member of the population has an equal chance of being included

in the sample.
● First a complete list of all the members of the population is prepared..
● Each element is identified by a distinct number.
● Two methods of selecting sample: lottery method, use of random
number generation table.
● Simple random sampling With replacement (SRSWR)
● Simple random sampling Without replacement (SRSWOR)
2. Systematic Random Sampling (Quasi-random)

● Sample elements are selected from the population at uniform intervals in

terms of time, order, or space.
● Steps:
- The entire population is arranged in a particular order.
- A sample interval is taken K = N/n, where N= population, n = sample
size
- A random number is selected from 1 to K. let it be A.
- Every Kth unit is selected after this.
- After A next unit of sample will be A+K.
3. Stratified Random Sampling

● Elements in the population are divided into homogeneous groups called

strata.
● Then, researchers use the simple random sampling method to select a
sample from each of the strata. Each group is called stratum.
● Stratum should be relatively homogenous and the strata should
contrast with each other.
● Entire population is divided into strata (groups) which are mutually
exclusive and collectively exhaustive.
● Mutually exclusive - if an element belongs to one stratum, it will not
belong to any other stratum.
● Collectively exhaustive - all the elements of various strata put together
cover all the elements of population.
Types:
● Proportionate stratified sampling: where the percentage of sample
taken from each stratum is proportionate to the actual percentage of the
stratum within the whole population
● Disproportionate stratified sampling : where the sample taken from
each stratum is disproportionate to the actual percentage of the stratum
within the whole population
4. Cluster Sampling:

● The population is divided into clusters.

● Elements within Clusters are heterogeneous but there is homogeneity
between clusters.
● In stratified sampling, strata happen to be homogenous but in cluster
sampling, clusters are internally heterogeneous.
● A cluster contains a wide range of elements and is a good
representative of the population.
● Complete enumeration of chosen clusters.
 Non- random Sampling Methods:
1. Convenience Sampling

● Sample elements are selected based on the convenience of a

researcher.
● Used to obtain information quickly and inexpensively.
● For ex- to know the opinion, people may be interviewed outside a
shopping mall.
● Mostly used for exploratory research to gain insight into problem.
● Should not be used for conclusive research.
2. Judgement Sampling

● Selection of the sampling units is based on the judgement of a

researcher.
● Experts choose what they believe to the best sample or
representative sample.
● Ex- A company wanting to launch a new product may use judgemental
sampling for selecting experts who have prior knowledge or experience
of similar product.
3. Snowball Sampling

● Survey respondents are selected on the basis of referrals from other

survey respondents.
● Used when it is difficult to identify members of desired population. Eg-
deep sea divers, families with triplets etc.
● Each respondent after being interviewed is asked to identify one or more
in the field.
4. Quota Sampling

● In quota sampling, certain subclasses, such as age, gender, income

group, and education level are used as strata. Stratified random
sampling is based on the concept of randomly selecting units from the
stratum.
● However, in case of quota sampling, a researcher uses non-random
sampling methods to gather data from one stratum until the required
quota fixed by the researcher is fulfilled.
Sampling and Non-
Sampling Errors
Sampling Error

● Occurs when the sample is not a true representative of the

population.

● Reasons:
1. Faulty selection of the sample. Ex - Judgement Sampling
2. Sometimes due to the difficulty in selection of a particular
sampling unit, researchers try to substitute that sampling unit
with another sampling unit which is easy to be surveyed.
Non-Sampling Error

● Errors that are not due to sampling but due to other forces.

● These occur at the stage of observation, ascertainment and

processing of data. Hence, they are present in both sampling
and complete enumeration.
Common Non-Sampling Errors

1. The respondent may not give the correct answer. (Response

Errors)
2. Chosen respondent may not be available to answer the
questions or refuse to answer certain questions. (Non-response
errors)
3. Errors at the time of coding, tabulation and computation.
Methods of Data
Collection
Primary Data

● Primary data are mainly collected by a researcher to address the

research problem.

● These are not readily available from various sources, rather the
researcher has to systematically collect it for a pre-specified
research problem.
Secondary Data

● Secondary data are the data that have already been collected by
someone else before the current needs of a researcher.

● The present researcher only uses these data with related reference and
never collects it from the field.
Benefits of Using Secondary Data

● The main advantage of using secondary data sources is that they

already exist; therefore, the time spent on the study is considerably less.

● There may be cases when the problem is general, such as the

demographic structure of a population at a particular region, in such
cases there is no meaning in collecting the primary data.

● Similarly, company’s financial data such as profit, sales, etc.

Limitations of Using Secondary Data

● The disadvantages of using secondary data are related to the fact that
their selection and quality, and the methods of their collection, are not
under the control of the researcher and that they are sometimes
impossible to validate.

● Moreover, the secondary data become outdated quickly. It is a big

restriction on the frequent use of the secondary data.
Classification of Secondary Data

● Internal and External.

● Internal secondary data are generated within the organization. (Internal

Records)

● External secondary data are obtained from the sources available outside
the organization.
Classification of secondary data sources
 Books, Periodicals, and Other Published Material

● The books, periodicals, and other published material generally

available in most of the libraries are big sources of secondary data.

● Libraries also provide access to some good research journals of the

country. Ex - Harvard Business Review, Research Journal of IIMs, XLRI
Jamshedpur Journal etc
 Reports and Publication from Government Sources

● Government sources also provide data. The accuracy and quality of these data
sources are unquestionable.
● Most researchers rely on government sources of data to conduct their research
programme.
● Reserve Bank of India (http://www.rbi.org.in) - (Information on Indian Economy)
● Planning Commission, Government of India(http://planningcommission.gov.in)
(Information on 5 Year plans and other economic indicators)
● Labourbureau.nic.in (information on labour statistics, wage surveys, condition of
women workers, minimum wages etc.
● Censusindia.gov.in
 Computerized Commercial and Other Data Sources

● There are various firms involved in selling data.

● For example, indiastat.com and CMIE are two private firms involved in
the accumulation and selling of the data.
● Thomson reuters.
● Capitaline
 Media Resources

● Some relevant and authentic information can also be gathered from the
broadcast and print media.
● The print and electronic media frequently conduct researches related to
personal life, professional life, life style, change in lifestyle, income
status, change in income status, and many other issues.
● Leading news papers such as The Economic Times, Pioneer, The Hindu,
The Indian Express, and many more national and regional newspapers have
plentiful information.
● Some magazines such as India Today, Outlook, Business India, Business
Today, Competition Success Review, and so on provide a lot of information
related to the current issues.
 Primary Data - Survey Method

● Survey means gathering information through respondents for any pre-

established research objective. A structured questionnaire is given to
the respondent and information is obtained.
● The major disadvantage is to handle the unwillingness of the
respondents to provide responses.
● Second disadvantage of the survey methods is the fact that the
individual characteristics of the interviewer or the way of
presentation of the questionnaire or the way of asking questions
makes a big difference in getting the responses.
 Classification of Survey Methods

● Personal Interview
● Telephone Interview
● Mail Interview
● Electronic Interview
 1. Personal Interview

● As the name indicates, personal interview is a method of data collection

through contacting a respondent personally.
● Personal interviews can be broadly classified into:
1. door-to-door interview,
2. mall intercept interview,
3. office interview,
4. self-administered questionnaire.
 1 (a). Door to Door Interview

● A traditional technique of getting the responses from the respondents at

their home.
● The interviewer contacts the respondents at their home in person and
seeks a face-to-face interview.
● In some cases like demonstration of product at home with interview, in-
home product tests and conduction of long in-depth interviews, door-to-
door interview technique is the only viable alternative a researcher has
got.
 1 (b). Mall Intercept Interview

● A respondent who actually is a visitor to a shopping mall is intercepted

by the interviewer for obtaining responses.
● It is easy to execute, but it also has some major disadvantages.
● Principally, the response rate is assumed to be higher, but in practice the
response rate happens to be very low.
● Reason - The respondents come to the malls for shopping and not for
answering the questions.
● There is a great possibility that the interviewer will try to contact a
respondent who looks friendly, and this results in a respondent
selection bias.
 1 (c). Office Interview

● An interviewer conducts an office interview at the workplace of the

respondents.
● When the research objective is to unfold the consumer attitude of any
industrial product or services, then probably home interview technique
will not be able to generate accurate responses.
● Office interviews are usually conducted after taking prior appointment
from the interviewee.
 1 (d). Self Administered Questionnaire

● In self-administered questionnaire, no interviewer is involved.

● A series of questions are presented to the respondents without the
intervention of the interviewer.
● While absence of intervention of the interviewer makes this interview
technique bias free from the interviewer’s angle on the one hand, a
personal clarification to some of the questions of the survey by the
interviewer is completely missing on the other.
 2. Telephone Interview

● In personal interview using telephone, the interviewers ask a series of

questions to the respondents and record the responses on the
questionnaire papers.
● It is cost efficient as it eliminates the cost incurred in travelling.
● Limitations of telephone personal interview is the inability of the interviewer
to have face-to-face communication with the respondent, “non-response”
of the respondent, Explaining some difficult questions is equally difficult for
the interviewer, unable to deal with a situation when a product
demonstration is extremely important.
 3. Mail Interview

● In a mail survey, the questionnaire is sent to the respondent through mail and the
respondent returns the filled questionnaire (providing his opinion about the
questions).
● In the mailing survey technique, the rate of return is a matter of concern.
● Some researchers favour providing some incentives to the respondents.
● Others believe that the incentive type has no impact on the return of the survey
(Church, 1993).
 3. Mail Interview (Contd.)

● Mail surveys generally provide accurate results because the respondent has
enough time to think and respond.
● Bias due to interviewer can also be controlled.
● Able to cover an extensive geographic area as compared with the personal
interview technique.
● Return time is not guaranteed.
● It eliminates the possibility of explanation of difficult-to-understand question
by the interviewer.
 4. Electronic Interview

● Electronic surveys in general are less expensive than the traditional

mail surveys because they do not involve printing, folding, envelope
stuffing, and mailing cost.
● In addition, non-involvement of the interviewer eliminates the
possibility of bias due to the interviewer. The obtained input data are
also of superior quality in this technique.
● Electronic surveys are also excellent facilitators in launching
international and cross-cultural research programmes.
 Primary Data - Observation Techniques

● Observation techniques involve watching and recording the behaviour

of test subjects or test objects in a systematic manner without
interacting with them.
● Observation research can be broadly classified as
1. direct versus indirect observation;
2. structured versus unstructured observation;
3. disguised versus undisguised observation;
4. and human versus mechanical observation.
 1. Direct versus Indirect Observation

- In direct observation, the researchers directly observe the behaviour of

a subject and record it.

- In indirect observation, the researcher observes outcome of a behaviour

rather than observing the behaviour.
 2. Structured versus Unstructured Observation

- In a structured observation, a clear guideline is provided to the observer

as what is to be observed and what is not to be observed.

- In an unstructured observation, the observer is free to observe what he or

she feels is important for a research.
 3. Disguised versus Undisguised Observation

- In disguised observation, the subject happens to be unaware that his or

her behaviour or action is being monitored by the observer.

- In undisguised observation, the subject happens to be aware that he or she

is being observed by an observer.
 4. Human versus Mechanical Observation

- Human observational techniques involve observation of the test subjects

or test object by a human being, generally an observer appointed by a
researcher.

- Mechanical observation techniques involve observation by a non-human

device.
 Advantages of Observation Techniques

Observation eliminates recall error as the observation is immediately

recorded on the place of observation.

Observations also allow an observer to collect data from the group of

subjects who are not able to provide written or verbal information.
 Limitations of Observation Techniques

- Inability to measure attitude or intentions of the subjects.

- Personal observation techniques require a lot of time and energy to be
executed.
- Disguised observation is sometimes unethical as the subject is unaware
that his or her action is being observed by the observer.
- From a practical standpoint, it is best to view the observation method as a
complement to survey methods, rather than to view it as a competitor.
Questionnaire Design and
Its Process
 What is a Questionnaire?
A questionnaire consists of formalized and pre-specified
set of questions designed to obtain responses from potential
respondents.

Questions in the questionnaire reflect the research objective

under investigation.
Questionnaire Design Process

1. Pre-Construction Phase
2. Construction Phase
3. Post-Construction Phase
1. Pre-Construction Phase

It consists of three steps:

● specific required information in the light of research objective,
● an overview of respondent’s characteristics, and
● decision regarding selecting an appropriate survey technique.
Step 1: Specific Required Information in the Light of
Research Objective

● The first and the foremost important decision relates to finding

the required information through a questionnaire.

● To generate specific information, the researcher should clearly

define the objective and the other research components such as
theoretical model, research questions, and hypotheses.
Step 2: An Overview of Respondent’s Characteristics

● While collecting the information, an overview of the

respondent’s characteristics is a vital consideration.
● While constructing a questionnaire, a researcher has to keep the
profile of a probable respondent in mind.
● Various factors such as the respondent’s qualification, age,
experience, income, marital status, occupation, and so on
have a decisive and impactful role in conducting a research.
Step 3: Decision Regarding Selecting an Appropriate
Survey Technique

● While constructing a questionnaire, a deep thinking process is

required to select an appropriate survey technique.
2. Construction Phase

It consists of six steps:

● Decision regarding question format :structured questions versus
unstructured questions
● Decision regarding question wording
● Decision regarding question sequencing
● Decision regarding question response choice
● Decision regarding the questionnaire layout
● Producing first draft of the questionnaire.
Step 1: Decision Regarding Question Format: Structured
Questions Versus Unstructured Questions

● Questionnaires use two types of question formats. These are open-

ended questions and closed-ended questions.

Open-ended Questions
 Closed-ended Questions

● Closed-ended questions are structured questions.

● The closed-ended questions provide response alternative to the

respondents.Respondents select the most appropriate one.

● The closed-ended questionnaires are generally faster to code, and

analyse.

● The closed-ended question format can be further divided into

dichotomous, multiple-choice questions, and scales.
 Step 2: Decision Regarding Question Wording

Wrong wordings impact the process of interpreting the questions, leading

at least some respondents to misinterpret how to respond and, thus,
reducing or destroying the usefulness of the questions or the series of
questions
Question Wordings Must Be Simple and Easy to
Understand
Vague or Ambiguous Words Must Be Avoided
 Double-Barrelled Questions Must Be Avoided

Double-barrelled questions are those with wordings such as “and” or “or.”

In a double-barrelled question, a respondent may agree to one part of
the question but not to the other part.
 Avoid Leading and Loaded Questions
A leading question is the one which clearly reveals the researcher’s
opinion about the answer to the question.

Wording elements in a loaded question allude to the universal belief or

rules of behaviour.
 Split Ballot Techniques (for Leading question)
● Leading question generally emphasizes either the positive or negative
aspect of the question.
● Sometimes, it becomes necessary to ask a question with either the
positive or negative aspect.
● This technique involves the construction of a single question in two
alternative phrases, and the question based on one phrase is
administered to half of the respondents and the question based on
the other phrase is administered to the other half of the
respondents.
Split Ballot Techniques (for Leading question)
 Avoid Using Overstated Words

The answer will always be overblown due to the first part of the
question, which generates a worry in the mind of the respondent and
results in a positive answer.
 Implied Assumptions Must Be Avoided

Above question has an implicit assumption that the discount policy on

bulk purchase offered by Company “A” is working excellent and by
answering “yes,” the company will continue its policy.
 Respondent’s Memory Should Not Be Overtaxed

- Some questions are based on respondent’s memory.

- But respondents tend to forget the incidents that are not important for
them.
 Generalization Must Be Avoided

Generalization means respondent’s belief, “what must happen” or “what

should happen.”
 Estimation Must Be Avoided
The respondent should not be left with the computation or estimation.
Ex.
What is the average per person consumption of pulses by your family
in past 6 months.

Instead the question must be divided into 2 components.

1. what is the consumption of pulses by your family in past 6 months?

2. how many members are there in your family?
 Respondent’s Ability to Answer Must Be Considered
A question targeted to officers older than 65 years to assess the
importance of Internet banking is as follows:

Targeting following question to young respondents may not be an

appropriate choice.

These respondents might not be able to answer these questions.

 Step 3:Decision Regarding Question Sequencing

Question sequence also plays a key role in generating the respondent’s

interest and motivation to answer the question.

Questions should have a logical sequencing in the questionnaire and

should not be placed abruptly.
 Step 3:Decision Regarding Question Sequencing

Question sequence also plays a key role in generating the

respondent’s interest and motivation to answer the question.

Questions should have a logical sequencing in the questionnaire

and should not be placed abruptly.
 Screening Questions

- Researchers generally begin with some screening questions to make

sure that the target respondent is qualified for the interview.

- In some cases, when the researcher is very sure about the qualification
status of the respondent, he or she does not incorporate the screening
question and starts from some “opening questions.”
 Opening Questions

- Should be simple, encouraging, and trust building. From the research

objective point of view, these questions may sometimes be little
irrelevant but should be good initiators.
- Should not seek in-depth information and should be as general as
possible.
- For example, a microwave company, trying to assess “shift in consumer
attitude” from traditional way of cooking, should ask a first opening
question as follows:
 Transition Statements
- The movement from one set of questions to another set requires
transition statements.

For example, a mineral water bottle manufacturing company is encouraged with the
expanding market. The company wants to assess the potential future market and hence
conducted a survey on non-users. Its researchers have identified various variables to get the
potential use, of which “awareness” and “taste” are important. It has prepared the first 11
questions with the first 5 questions based on the “awareness” and the next 6 questions on
“taste.” After asking the first set of 5 questions, a researcher moves to the second set of 6
questions to get the potential consumer feeling for mineral water taste. Thus, before asking the
next set of 6 questions, a transition statement is required to make the respondent familiar with
the coming questions. Hence, a transition statement “Now, I would like to understand your
opinion about the mineral water taste” will develop respondent’s connectivity for the next set of
6 questions related to “taste,” and he or she will be in a comfortable state of mind to answer these
questions.
 Difficult to Answer Questions

- Difficult to answer, sensitive, or complicated questions should be

placed later in the questionnaire.

- Placing it first will confuse the respondent and he or she will tend to
terminate the interview process.
 Identification and Categorization Questions

- Identification questions are used to generate some basic

identification information such as name, mailing address, office
phone number, personal phone number, or cell phone number.

- Categorization questions are mainly used to generate demographic

information. For example, researchers generally want to generate the
information related to age, experience, gender, and occupation of
the respondents.
 Logical Order of Questioning
- In a questionnaire, the questions must flow in a logical sequence.
- Three approaches to place the questions in a logical sequence; they
are funnel technique, work technique, and sections technique.
- Funnel technique suggests asking general questions first and then
the specific questions.
- Work technique suggests that difficult-to-answer, sensitive, or
complicated questions should be placed later in the questionnaire.
- The third technique is the section technique in which questions are
placed in different sections with respect to some common base.
 Step 4: Decision Regarding Question Response Choice

- It is important to understand that too many response choices will

burden the respondent and he or she will be puzzled while answering.

- Few response choices will not be able to cover all ranges of

possible alternatives.

- As a general rule, the researchers present a question with five to

seven response alternatives.
 Step 5: Decision Regarding Questionnaire Layout

- Questionnaire layout is important to enhance the response rate.

- Studies reveal that a user-friendly format, and to some extent colour,

is valuable to increase mail survey response rate.

- The appearance of a questionnaire is particularly important in mail

surveys because the instrument, along with the preliminary letter and/
or cover letter, must sell itself and convince the recipient to complete
and return it.
 Step 6: Producing First Draft of the Questionnaire

- Printing on a poor, quality paper or an unprofessional look of the

questionnaire may generate a non-serious feeling among the
respondents.
- So, the questionnaire may be printed on a good, quality paper and
must have a professional look.
- The appearance of the front cover on a mail questionnaire and the
nature of first questions have an important influence on the
respondent’s decision to complete the questionnaire.
 Phase III: Post-Construction Phase

- It consists of four steps:

1. Pre-testing of the questionnaire

2. Revisiting the questionnaire based on the inputs obtained from the pre-
testing
3. Revising final draft of the questionnaire
4. Administering the questionnaire and obtaining responses.
 Step 1: Pre-Testing of the Questionnaire

- Pre-testing of the questionnaire involves administering the

questionnaire to a small sample of the population to identify and
eliminate the potential problems of the questionnaire, if any.

- Researchers generally use two common procedures to pre-test:

protocol analysis and debriefing.
 Step 1: Pre-Testing of the Questionnaire (Contd.)

- Using protocol analysis, a researcher asks the respondent to “think aloud”

while answering the question.
- Debriefing is an interview conducted when a respondent has filled the
questionnaire. After completing, the respondents are informed that the
questionnaire they have just filled was a pre-test questionnaire and are
requested to share their views about various dimensions of the
questionnaire. They are also requested to find out the problems with the
questionnaire, which they realized while filling it.
Step 2: Revisiting the Questionnaire Based on the Inputs
Obtained from Pre-Testing

- To enhance the accuracy, after incorporating suggestions from the pre-

testing, a researcher can go for second pre-testing.

- It is always possible that the second pre-testing may also reveal

some of the problems of the questionnaire.
 Step 3: Revised Final Draft of the Questionnaire

- At this stage, the researcher once again carefully examines the

questionnaire.
- Insertions and deletions of the previous stage must be re-checked to
provide the desired accuracy.
- The researcher makes the questionnaire “ready to administer” by
eliminating all the minute mistakes and tries to make it error free.
 Step 4: Administration of the Questionnaire and
Obtaining Responses

- At this stage, the researchers administer the questionnaire to the

respondents and obtain the responses.
- These responses are coded, data are tabulated, and appropriate
statistical techniques are applied to analyse the data.

- .