Questionnaire Design

ATTITUDE AND SOCIAL SCALES

Attitude scaling is the process of assessing an

attitudinal disposition using a number that

represents a person's score on an attitudinal

continuum ranging from an extremely favorable

disposition to an extremely unfavorable one.

People have certain feelings, perceptions and

behavior towards other things, people, places and

times. These feelings and perceptions are called

attitudes and social scientists frequently desire to

know people's attitudes. These are measured by

attitude scales.

Rese

arc

h M

eth

od

olo

gy (P

rava

t Upre

ty)

7/2

3/2

01

4

1

1. SIMPLE ATTITUDE SCALES:

i) The simple category (also called a dichotomous

scale) offers two mutually exclusive choices such

as yes and no, important and unimportant, agree

and disagree. This response strategy is particularly

useful for demographic questions or where a

dichotomous response is adequate.

Example:

“I plan to purchase a MindWriter laptop in the next 12

months.”

Yes

No

Rese

arc

h M

eth

od

olo

gy (P

rava

t Upre

ty)

7/2

3/2

01

4

2

WHEN THERE ARE MULTIPLE OPTIONS FOR THE RATER BUT ONLY ONE

ANSWER IS SOUGHT, THE MULTIPLE-CHOICE, SINGLE RESPONSE SCALE IS

APPROPRIATE.

Example:

“What newspaper do you read most often for financial

news?”

New Business Age

BOSS

Karobar

Abhiyan

The Kathmandu Post

The Himalayan Times

Other (specify:……….)

Rese

arc

h M

eth

od

olo

gy (P

rava

t Upre

ty)

7/2

3/2

01

4

3

THE MULTIPLE-CHOICE, MULTIPLE RESPONSE SCALE (ALSO CALLED A

CHECKLIST), ALLOWS THE RATER TO SELECT ONE OR SEVERAL

ALTERNATIVES.

Example:

“Check any of the sources you consulted when

designing your new home.”

Online planning services

Magazines

Independent contractor/builder

Developer’s models/plans

Designer

Architect

Other (specify:……….)

Rese

arc

h M

eth

od

olo

gy (P

rava

t Upre

ty)

7/2

3/2

01

4

4

LIKERT SCALE (SUMMATED RATING SCALES):

Named after its developer, Rensis Likert, the Likert

Scale is a widely used rating scale that requires the

respondents to indicate a degree of agreement or

disagreement with each of a series of statements

about the stimulus objects. Typically, each scale item

has five response categories, ranging from “strongly

disagree” to “strongly agree”.

Rese

arc

h M

eth

od

olo

gy (P

rava

t Upre

ty)

7/2

3/2

01

4

5

Statement Strongly

Disagree

Disagree Neutral Agree Strongly

Agree

1 2 3 4 5

I get a feeling of

accomplishment

from the work I

am doing.

I find real

enjoyment in

my work.

JOB SATISFACTION RESEARCHR

ese

arc

h M

eth

od

olo

gy (P

rava

t Upre

ty)

7/2

3/2

01

4

6

Statement Strongly

Disagree

Disagree Neither

Agree nor

Disagree

Agree Strongly

Agree

1 2 3 4 5

BDS sells

high quality

merchandise

BDS has poor

in-store

service

I like to shop

at BDS

B. DEPARTMENT STORE RESEARCH [EX:-

BANESHWOR DEPARTMENTAL STORE (BDS)]R

ese

arc

h M

eth

od

olo

gy (P

rava

t Upre

ty)

7/2

3/2

01

4

7

SEMANTIC DIFFERENTIAL (SD) SCALE:

The semantic differential is a seven-point rating

scale with endpoints associated with bipolar labels

that have semantic meaning. In a typical

application, respondents rate objects on a number

of itemized, seven-point rating scales bounded at

each end by one of two bipolar adjectives, such as

“Pleasant” and “Unpleasant”.

Rese

arc

h M

eth

od

olo

gy (P

rava

t Upre

ty)

7/2

3/2

01

4

8

EXAMPLE: ADAPTING SD SCALES FOR BDS

Convenience of reaching the store from your location

Nearby _ : _ : _ : _ : _ : _ : _ Distant

Short time required to reach store _ : _ : _ : _ : _ : _ : _ Long time required to reach store

Difficult drive _ : _ : _ : _ : _ : _ : _ Easy Drive

Difficult to find parking place _ : _ : _ : _ : _ : _ : _ Easy to find parking place

Products offered

High quality _ : _ : _ : _ : _ : _ : _ Low quality

Numerous brands _ : _ : _ : _ : _ : _ : _ Few brands

Unknown brands _ : _ : _ : _ : _ : _ : _ Well-known brands

Fully stocked _ : _ : _ : _ : _ : _ : _ Under stocked

Individual items on a semantic differential scale may be scored on either a -3 to +3 or 1 to 7 scale.

Rese

arc

h M

eth

od

olo

gy (P

rava

t Upre

ty)

7/2

3/2

01

4

9

STAPEL SCALES

The Staple scale, named after its developer, Jan Stapel, is aunipolar rating scale with 10 categories numbered from -5 to+5, without a neutral point (Zero). This scale is usuallypresented vertically. Respondents are asked to indicate howaccurately or inaccurately each term describes the object byselecting an appropriate numerical response category. Thehigher the number, the more accurately the term describesthe object. The scale is composed of the word (or phrase)identifying the image dimension and a set of 10 responsecategories for each of the three attributes. Fewer responsecategories are sometimes used. Participants select a plusnumber for the characteristics that describes the attitudeobject. The more accurate the description, the larger is thepositive number. Similarly, the less accurate the description,the larger is negative number chosen.

Rese

arc

h M

eth

od

olo

gy (P

rava

t Upre

ty)

7/2

3/2

01

4

10

EXAMPLE: FOR BANESHWOR DEPARTMENTAL

STORE (BDS)

+5 +5

+4 +4

+3 +3

+2 +2

+1 +1

High Quality Poor Service

-1 -1

-2 -2

-3 -3

-4 -4

-5 -5

Rese

arc

h M

eth

od

olo

gy (P

rava

t Upre

ty)

7/2

3/2

01

4

11

RANKING QUESTION

Give the rank to the following brands of toothpaste

according to your preference

(1 is most preferred and 5 is least preferred)

7/2

3/2

01

4

12

Rese

arc

h M

eth

od

olo

gy (P

rava

t Upre

ty)

Name of the Brand Rank

Close Up

Pepsodent

Dabur

Ganozhi

Colgate

RATING QUESTION

Give the score to the following brands of toothpaste

according to your preference (out of 10)

7/2

3/2

01

4

13

Rese

arc

h M

eth

od

olo

gy (P

rava

t Upre

ty)

Name of the Brand Score (Out of

10)

Close Up

Pepsodent

Dabur

Ganozhi

Colgate

QUESTIONNAIRE DESIGN

The main tool that is used in survey research is questionnaire.

A questionnaire is a formal list of questions designed to gather

responses from respondents on a given topic. Thus, a

questionnaire is an efficient data collecting mechanism when

the researcher knows exactly what is required and how to

measure the variables of interest.

A questionnaire involves several steps, including writing

question items, organizing the question items on a

questionnaire, administering the questionnaire and so on. We

should remember that a collection of questions does not make

a questionnaire. The questions must be organized into a

coherent, visually pleasing format. This process involves

paying attention to the design of the questionnaire. An

organized questionnaire is much easier and more enjoyable for

the respondent to complete. This may also increase the

response and completion rates.

Me

tho

do

log

y (P

rava

tU

pre

ty)

7/2

3/2

01

4

14

QUESTIONNAIRE…..

A good questionnaire accomplices the researcher’s

objectives. Surveys must be custom-built to the

specification of given research purposes, and they

are much more than a collection of unambiguous

questions. A number of constraints are imposed on

the development of an appropriate questionnaire.

For example, the number, form, and ordering of the

specific questions are partly determined by the data

collection method. The respondent’s willingness

and ability to answer also influences the final

questionnaire format. That wording and sequence

of questions can facilitate recall and motivate more

accurate responses.

Rese

arc

h M

eth

od

olo

gy (P

rava

t Upre

ty)

7/2

3/2

01

4

15

ACTIVITIES TO BE REQUIRED TO MAKE A

QUESTIONNAIRE

Although each questionnaire must be designed with specific research objectives in mind, there is sequence of logical steps that every researcher must follow to develop a good questionnaire:

1.Plan what to measure

Revisit the research objectives

Decide on the research issue of your questionnaire

Get additional information on the research issue from secondary data sources and exploratory research

Decide on what is to be asked under the research issue

2. Formulate questions to obtain the needed information

In each issue, determine the content of each question

Decide on the format of each question

Re

se

arc

h M

eth

od

olo

gy (P

rava

tU

pre

ty)

7/2

3/2

01

4

16

3. Decide on the order and wording of questions and on the layout of the questionnaire

Determine how the question is to be worded

Evaluate each research question on the basis of comprehensibility, knowledge and ability, willingness\inclination of a typical respondent to answer the question

Lay out the questions in each subtopic to get a single questionnaire

Group all the questions in each subtopic to get a single questionnaire

4. Using a small sample, test the questionnaire for omissions and ambiguity

Read through the whole questionnaire to check whether it makes sense and it measures what it is supposed to measure (validity)

Check the questionnaire for error

Check the physical appearance

Pretest the questionnaire

5. Correct the questions (and pretest again, if necessary) and give final shape

Rese

arc

h M

eth

od

olo

gy (P

rava

t Upre

ty)

7/2

3/2

01

4

17

The questionnaire design that draws out accurate information, that canbe completed easily by the interviewer, that flows well, and that leavesthe respondents feel satisfied for their worthwhile participation in thatresearch, can be described as an effective design.

Information desired:

What information would we want to collect? We should make a plan ofour information requirements. Collecting unnecessary information mayconsume more of our time and resources. The respondents are alsoirritated by long questionnaires. We should also avoid questions that aretoo personal. If one question antagonizes a respondent, he or she isquite likely not to answer any of them.

Type and form of questions:

One of major decision area in question design is the degree and form ofstructure imposed on the participant. The various strategies offer optionsthat include unstructured response (or open ended response, the freechoice of words) and structured response (or closed response, specifiedalternatives provided). Open-ended questions allow respondents toanswer them in any way they choose. A closed question, in contrast,would restrict the respondents within the alternative given.

Rese

arc

h M

eth

od

olo

gy (P

rava

t Upre

ty)

7/2

3/2

01

4

18

Length:

Simple, short questions are preferable than long ones. The longer the questionnaire, the more it costs to administer and to interpret the data obtained. Long questions consume more time of respondents. This may discourage the respondents to complete the questionnaire.

Wording:

A great precaution is necessary in wording the questions. Proper wording and proper language are absolutely essential. The words should be simple, clear and unambiguous.

Order:

The related questions should be logically ordered. Question order is especially important when multiple-choice questions are used. Good questionnaire are funnel-shaped. They move from general to particular. Well-organized questionnaire keeps the respondent’s attention on one issue at a time, rather than jumping from issue to issue. The order and flow of questions should be logical to the respondents.

Physical appearance:

Attention should be paid in order to give a good physical appearance to the questionnaires so as to get good response from the respondents. The matters that require special attention include quality and size of paper, quality of typing or printing, attractive presentation of question items, including margins and spacing.

Rese

arc

h M

eth

od

olo

gy (P

rava

t Upre

ty)

7/2

3/2

01

4

19

COMPONENTS OF A QUESTIONNAIRE:

Explanation information (Administrative questions)

Classification information (Classification questions)

Basic information (Target questions)

Rese

arc

h M

eth

od

olo

gy (P

rava

t Upre

ty)

7/2

3/2

01

4

20

EXPLANATION INFORMATION:

The researcher provides explanation information to

the respondents to explain the purpose of the study.

This information is usually given at the beginning of

the questionnaire in the form of a letter or

instructions. Explanation information states i. the

purpose of the study, ii. makes an appeal for

responses, and iii. provides information on

completing the questionnaire properly.

Rese

arc

h M

eth

od

olo

gy (P

rava

t Upre

ty)

7/2

3/2

01

4

21

CLASSIFICATION INFORMATION:

Classification questions usually cover sociological-demographic variables that allow participants answersto be grouped so that patterns are revealed and can bestudied. These questions usually appear at the end of asurvey. Most of the commonly gathered classificationinformation includes age, gender, education, maritalstatus, family income, occupation etc. This informationcan be used for segmenting the samples by variouscharacteristics and attributes of interest. Classificationinformation thus enables the researcher to analyze thedata obtained through tabulation. Such information isalso important for drawing profile of the respondentsand determining significant differences between groupsof respondents.

Rese

arc

h M

eth

od

olo

gy (P

rava

t Upre

ty)

7/2

3/2

01

4

22

BASIC INFORMATION:

This is the main part of the questionnaire. Basic

information desired from the study, of course, refers

to that information which is needed to solve the

problem, which prompted the study to be

undertaken. This part of the questionnaire thus

covers all necessary subjects under investigation

adequately. The basic information section may be

only a few questions in length or it may be several

pages, depending upon the amount of data sought.

Rese

arc

h M

eth

od

olo

gy (P

rava

t Upre

ty)

7/2

3/2

01

4

23

MEASURING THE QUESTIONNAIRE ADMINISTERING:

Contact rate: Making contacts with respondents could be a problem in some cases. The proportion of addresses or eligible names with which the researcher makes contact measures this rate.

Response rate: Non response could also be a problem in some research studies. The proportion of contacts that result in interviews measures the response rate.

Completeness rate: Questionnaires returned incomplete are useless. The proportion of information obtained to that desired measures the completeness rate.

Accuracy rate: The accuracy rate is defined as the ratio of measured to true value.

Rese

arc

h M

eth

od

olo

gy (P

rava

t Upre

ty)

7/2

3/2

01

4

24