Questionnaire Design

&
Scaling

ashishpillai@gmail.com
What is a Questionnaire?
A list of questions for obtaining information
from respondents

Allows data to be collected in a standardized

way so that the data can be analysed

ashishpillai@gmail.com
What is the Big Deal
Then?
Making questionnaires is never easy
Questions have to be:
Relevant

In the correct form

In the correct language

Enough to generate required amount of data

ashishpillai@gmail.com
Steps in Making a
Questionnaire
1. Write Title and Objectives of your study.

2. Formulate statistical analysis plan for each objective and

enlist variables that will be needed to be studied
3. Finalise who your respondents will be.

4. Review literature to identify already validated

questionnaires measuring similar constructs
5. Compose a draft of your questionnaire.

6. Test it and revise the draft.

7. Assemble the final questionnaire.

ashishpillai@gmail.com
Type and Form of
Questions is Key
Do You Like Sweets? YES NO

Do you reach class on time? YES NO

Agree Neither Agree Disagree

Agree Disagree
Strongly Nor Disagree Strongly

I like eating
sweets
Always Often Sometimes Rarely Never

I reach class on
time

ashishpillai@gmail.com
Types of Questions
Open Ended Likert Scale

Multiple Choice Dichotomous

Rating Ranking

ashishpillai@gmail.com
What is “Scaling”?
The generation of a continuum upon
which measured objects are located
In simple words…. Making a Scale!

What a scale actually means and what we can do

with it depends on what its numbers represent or
it’s level of measurement

ashishpillai@gmail.com
The Two “Kinds” of Scales
Comparative Non-Comparative

Scales in which one Scales in which

object, concept, judgment is made
or person is compared without reference to
with another on another object, concept,
a scale …. or person….

Do you prefer color A or How do you feel about color

color B? B?
ashishpillai@gmail.com
Scale Characteristics
Description: The unique labels or descriptors that are used
to designate each value of the scale
Order: The relative sizes or positions of the descriptors.
Order is denoted by descriptors such as greater than, less
than, and equal to….
Distance: The characteristic of distance means that
absolute differences between the scale descriptors are
known and may be expressed in units
Origin: The scale has a unique or fixed beginning or true
zero point
ashishpillai@gmail.com
The Four levels of
Measurement
1. Nominal

2. Ordinal

3. Interval

4. Ratio

ashishpillai@gmail.com
Two Categories of Levels of
Measurements
Categorical
Binary (1,0…. Yes, No…..)

Nominal

Ordinal

Continuous
Interval

Ratio
ashishpillai@gmail.com
Summarizing Levels of
Measurement

ashishpillai@gmail.com
Which Scale?

Nominal

Ordinal

Interval

Ratio

ashishpillai@gmail.com
Which Scale?

Nominal

Ordinal

Interval

Ratio

ashishpillai@gmail.com
Which Scale?

Nominal

Ordinal

Interval

Ratio

ashishpillai@gmail.com
Which Scale?

Nominal

Ordinal

Interval

Ratio

ashishpillai@gmail.com
Which Scale?

Nominal

Ordinal

Interval

Ratio

ashishpillai@gmail.com
Which Scale?

Nominal

Ordinal

Interval

Ratio

ashishpillai@gmail.com
It is all About How it is
Scored!
If the variable we are measuring is scored using “non-
quantitative” answers, it is NOMINAL
If the scores given can be ranked but you have no idea how
much is the difference between two two (e.g. how many
marks difference between students who stood 1st and the
one who stood 2nd)… It is ORDINAL
If the scores can be ranked and you know the difference
also… e.g. Age, Income, Weight etc… it is either INTERVAL
or RATIO
If zero score means absence of that variable…. (e.g.
income)….. Then it is Ratio
ashishpillai@gmail.com
What Can be Measured
and How
Object: A tangible item in a person’s environment that can
be clearly and easily identified through his or her senses
Construct: A variable that examines subjective or abstract
properties that are intangible characteristics and cannot be
directly observed or measured……..concepts that are
measured with multiple variables

1. Identify and define what is to be measured,

2. Decide how to precisely measure,
3. Measure.

ashishpillai@gmail.com
Some Objects &
Constructs

ashishpillai@gmail.com
What are Variables?
Variable: Something whose value can change

Independent Variable: The variable that is manipulated

to study the effects on the dependent variable

Dependent Variable: The variable that you are interested

in and seek to measure in your research

Extraneous Variable: Undesirable variables that

influence the relationship between the variables that an
experimenter is examining….Variables not under study but
which influence the variables that are being studied
ashishpillai@gmail.com
Terms
Attribute: A characteristic of an object or entity…… A
qualitative characteristic that a unit of a population either
possesses or does not possess
Population Parameter: A parameter is a value, usually
unknown (and which therefore has to be estimated), used to
represent a certain population characteristic
Can be “descriptive parameters”…. E.g. Mean
Can be “relationship parameters”….. E.g. Correlation

Statistic: A single measure of some attribute of a

sample (not the entire population)
ashishpillai@gmail.com
Scales

ashishpillai@gmail.com
Paired Comparisons

ashishpillai@gmail.com
Paired Comparison
1. Make a list of all of the options that you want to compare.
Assign each option a letter (A, B, C, D, and so on) and note
this down.
2. Mark your options as both the row and column headings on
the worksheet. This is so that you can compare options
with one-another.
3. Block out cells where an option is comparing with itself or
where comparisons are being duplicated
4. Within each blank cell, compare and decide which of the
two options is most important and note it down in that cell

ashishpillai@gmail.com
Paired Comparison
5. Score the difference in importance between the
options…..
A. Zero “0” to “no difference” or “same importance”
B. One “1” to the option that is “more important” than the
other
C. Two “2” to the option that is “a lot more” or “much more”
important than the other
6. Consolidate scores for each option and pick the
one with the highest score….

ashishpillai@gmail.com
Paired Comparison – An
Example
You are deciding between three options on how to
spend a weekend…. The three options….

Study Mkt. Research (A )

Prepare for Farewell (B)

Sleep (C)

ashishpillai@gmail.com
Paired Comparison

A B C
A B (3) C (1)

B B (1)

C
ashishpillai@gmail.com
 Rank Order
Rate the following three colleges according to the three
attributes (academics, placements and activities) on a scale
from 1 to 3, where 1 is the best and 3 is the worst.
Academics Placement Activities
s
College A
College B
College C

ashishpillai@gmail.com
Constant Sum
Please allocate 100 points to the below given five
characteristics of a college. The more important a
characteristic is to you, the more points you should allocate it.
However the total of the points should remain 100.
Characteristics Points
Faculty
Placements
Industry Linkages
Training Activities
Projects
100
ashishpillai@gmail.com
 Non Comparative Scales

Continuous Rating Itemized Rating

Scale Scale

ashishpillai@gmail.com
Continuous Rating Scale
You will ask the respondent to rate the objects by
placing a mark at the appropriate position on a line
that runs from one extreme of the criterion variable
to the other. E. g…..

How would you rate Reliance Fresh as a department store?

Probably the worst Probably the best

ashishpillai@gmail.com
Itemized Rating Scales
The respondents are provided with a scale that has a
number or brief description associated with each
category.

The categories are ordered in terms of scale position,

and the respondents are required to select the
specified category that best describes the object being
rated.

The commonly used itemized rating scales are the

Likert, semantic differential, and Stapel scales.

ashishpillai@gmail.com
The Likert Scale
Requires the respondents to indicate a degree of
agreement or disagreement with each of a series of
statements about the stimulus objects

The analysis can be conducted on an item-by-item

basis (profile analysis), or a total (summated) score can
be calculated.

When arriving at a total score, the categories assigned

to the negative statements by the respondents should
be scored by reversing the scale.

ashishpillai@gmail.com
 An Example of Likert
Scale
Neither Agree Disagree
Agree Strongly Agree Disagree
Nor Disagree Strongly
We encourage customer
comments and complaints
because they
help us do a better job
After-sales service is an
important part of our business
strategy
We have a strong commitment
to our customers
We are always looking at ways
to create customer value in our
products

ashishpillai@gmail.com
Fit for a Sales Profile?
SA A NAN D S
D D

I can talk to strangers

easily
I am not afraid of failure
I rarely feel any hesitation
I like challenging tasks

ashishpillai@gmail.com
Fit for a Sales Profile?
SA A NAN D S
D D

I can talk to strangers 5 30 30 20 1

easily 5

I am not afraid of failure 0 35 35 20 1

0
I rarely feel any hesitation 5 40 25 25 5
I like challenging tasks 35 45 20 0 0

ashishpillai@gmail.com
Fit for a Sales Profile?
5 4 3 2 1
2 1 0 -1 -2
SA A NAN D S
D D

I can talk to strangers 5 30 30 20 1

easily 5

I am not afraid of failure 0 35 35 20 1

0
I rarely feel any hesitation 5 40 25 25 5
I like challenging tasks 35 45 20 0 0

ashishpillai@gmail.com
Likert Type Vs Likert Scale
When you have individual questions that use the five
point scale, they are called “LIKERT TYPE”….
When you use a set of statements with a Likert Scale to
measure one particular variable, that bunch of
statements is called a “LIKERT SCALE”

Data generated from “Likert Type” also known as

“Likert Item” questions are treated as ordinal

Data generated by “Likert Scale” questions are treated

as interval
ashishpillai@gmail.com
 A Likert Scale is Made
Up of Likert Items

ashishpillai@gmail.com
Examples of Likert Scales
The SERVQUAL

The MORTN Scale

The Big Five Inventory

ashishpillai@gmail.com
The Semantic Differential
Scale
A seven-point rating scale with end points associated
with bipolar labels that have opposite semantic
meaning

Individual items on a semantic differential scale may be

scored on either a -3 to +3 or a 1 to 7 scale

Analysis is performed by assigning scores to the seven

points

ashishpillai@gmail.com
Examples of Semantic Differential

The new Maruti Swift is :

Powerful --:--:--:--:--:--:--: Weak

Unreliable --:--:--:--:--:--:--: Reliable
Attractive --:--:--:--:--:--:--: Repulsive

ashishpillai@gmail.com
The Stapel Scale
A unipolar rating scale with ten categories numbered
from -5 to +5, without a neutral point (zero).

This scale is usually presented vertically

The data obtained by using a Stapel scale can be

analyzed in the same way as semantic differential data

ashishpillai@gmail.com
Example of Stapel Scale
Please rate Reliance Fresh on the service they provide,
the variety in their stores and the ambience of the store
+5 +5 +5
+4 +4 +4
+3 +3 +3
+2 +2 +2
+1 +1 +1
Service Variety Ambience
-1 -1 -1
-2 -2 -2
-3 -3 -3
-4 -4 -4
-5 -5 -5

ashishpillai@gmail.com
Some Questionnaires…
To Study Market Orientation of Firms

To Analyse Attitude of SME Business Owners Towar

ds Training

To Study the How Marketing is Implemented in SM

Es

An MBA final project questionnaire…

ashishpillai@gmail.com
Suggested Sequence of
Questions
Easy Demographic

Context Building

Information gathering
Probing

Difficult Demographic (if any needed)

Closing

ashishpillai@gmail.com
Some Tips…
Write down each objective on a page or a paper…
Then write down in “normal English” all questions
that come to your mind for that objective…
Decide plan for analysis: Tools & Techniques
Now use scaling methods to write questions in a
manner which will generate type of data needed for
the intended analysis plan

ashishpillai@gmail.com
Some Tips
Use the respondent’s language and vocabulary…

Try to keep it as small as possible without

compromising statistical completeness

Make the questionnaire look good!

Keep length limited

ashishpillai@gmail.com
Some Tips
Do you like drinking tea and/or coffee?

Ask about tea and in a separate question ask about

coffee

Sometimes leaving the question open ended is a

better option… e.g….. Income: ___________

Use Google Forms / Surveymonkey / Fluidsurvey

ashishpillai@gmail.com
How Do We Make a Questionnaire?

Identify Problem
Problem Statement

Draft Objectives &

Questionnaire Statistics

Test Final
Questionnaire Questionnaire

ashishpillai@gmail.com
The Research
How do students use internet?

How do students of different disciplines

use the net?

Has it changed the way we study?

ashishpillai@gmail.com
The Title
A Study of Internet Use Among Graduate
Students
Internet Use Among Graduate Students: A
Comparison Across Disciplines
Internet and Graduate Education: A
Comparative Study Across Disciplines
Internet Use Among Graduate Students: An
Exploratory Study
ashishpillai@gmail.com
Objectives of the Study
To study and compare the internet
use by graduate students

To analyze the use of internet as an

aid in the learning process by
students

ashishpillai@gmail.com
Use…
Do you use the internet?
How much time do you use it in a day?
Where do you access the net?
At home?
At college?
Do you own a laptop and / or desktop?
Smartphone?
2G / 3G / 4G
ashishpillai@gmail.com
Learning
Do you use the net for study?
How?
Do you search for things to study / assignment?
How important is net for your studies?
Has your use of net for studies increased?
Has your approach to studying something changed
because of the net?
How?
ashishpillai@gmail.com
Stats…
Means, Std. Deviations
Anova
Chi
Cluster
Factor

ashishpillai@gmail.com
The Questionnaire
Name: _____________

Stream of Study: _________

Semester: ________
College: _________

Univ.: ___________

ashishpillai@gmail.com
Normal language to
Qustionnaire
Do you use the Internet? Yes No

If Yes, how often?

All the Frequentl Sometime Rarely Never
Time y s

If Yes, how often in a day?

All the Frequentl Sometime Rarely
Time y s

ashishpillai@gmail.com
Isn’t this Better
How often do you use internet on an
average in one day?

All the Frequentl Sometime Rarely Never

Time y s

ashishpillai@gmail.com
Another Question: How
Access???
How do you access the net?
1 = Never ….. 5 = Very Frequently

1 2 3 4 5
Desktop
Laptop
Tablet PC
Phone

ashishpillai@gmail.com
For Study
Please indicate your usage of internet for
the following:

1 2 3 4 5
Assignments
Projects
Preparing for
exams

ashishpillai@gmail.com