HOW TO DESIGN A QUESTIONNAIRE

Four aspects of the questionnaire. For explanatory research Measures of the dependent variable(s): clarify what it is you are trying to explain and develop questions to this Measures of the independent variable(s): .... Wording questions: Is the language simple? Can the question be shortened?

Dr Kim D Nguyen Institute for Educational Research

Ho Chi Minh City - Vietnam

HOW TO DESIGN A QUESTIONNAIRE

Four aspects of the questionnaire

For explanatory research

1) Measures of the dependent variable(s):

clarify what it is you are trying to explain

and develop questions to this

2) Measures of the independent variable(s):

Make sure you have questions to tap each

of the causal variables

Four aspects of the questionnaire

For explanatory research (cont.)

3) Measures of test variable(s): These are

variables which help clarify the nature of the links between independent and

dependent variables

4) Background measures: Questions about

characteristics such as age, sex, religion, education, occupation, marital status,

stage in the life cycle, ethnic group and so on

Question content

There are four types of questions:

Behavior, beliefs, attitudes and attributes (Dillman, 1978).

BEHAVIOR:

Questions to establish what people do.

BELIEFS:

What people believe is true or false.

Question content (cont.)

ATTITUDES:

Questions try to establish what they think is

desirable.

ATTRIBUTE:

Questions are designed to obtain information

about the respondent’s characteristics

Wording questions

1) Is the language simple?

2) Can the question be shortened?

3) Is the question double-barrelled? – Is

she rich and intelligent? 4expl

4) Is the question leading?

5) Is the question negative?

6) Is the respondent likely to have the

necessary knowledge?

Wording questions (cont.)

7) Will the words have the same meaning

for everyone?

8) Is there a prestige bias?

9) Is the question ambiguous?

10) Do you need a direct or indirect

question?

Wording questions (cont.)

11) Is the frame of reference for the

question sufficiently clear?

12) Does the question artificially create

opinions?

13) Is personal or impersonal wording

preferable?

14) Is the question wording unnecessarily

detailed or objectionable?

Wording questions (cont.)

15) Does the question have dangling

alternatives?

16) Is the question likely to produce a

response set?

Avoid making certain answers appear

normal or unusual

Open and closed format questions (cont.)

Disadvantages:

- Create false opinions

- Give an insufficient range of alternatives

- It’s necessary to put s lot of thought into developing alternative responses The

range must be exhaustive: a thorough

range of responses must be listed to avoid biasing responses

Open or closed questions?

Depends on how many factor such as the question content, respondent motivation,

method of administration, type of

respondents, access to skilled coders to

code open-ended questions and the

amount of time available to develop a good set of unbiased responses

Open or closed questions?

Gallup (1947):

- A closed question to see if the respondent has thought about or is aware of the issue

- An open question to get at general

feelings on the matter

- A closed question to get at specific

aspects of the issues

Open or closed questions? (cont.)

Gallup (1947):

- Open or closed questions to find out

respondents’ reasons for their opinions

- Close question to find out how strongly the opinion is held

Types of forced-choice response formats

1) Likert-style formats

2) Semantic differential formats

3) Checklists

4) Ranking formats

5) Attitude choices rather than

agree-disagree statements

6) Direction, extremely and intensity of

attitudes