Some General Rules for Designing Good Survey Instruments

1. Some General Rules for Designing Good Survey Instruments

2. Wording Questions • Principle 3: a survey question should be worded so that every respondent is answering same questions • Principle 3a; to the extent possible, the words in questions should be chosen so that all respondents understand their meaning, and all respondents have the same sense of what the meaning is.

3. Wording Questions • Principle 3: a survey question should be worded so that every respondent is answering same questions • Principle 3b; To the extents the words or terms must be used that have meanings that are likely not to be shared, definitions should be provided to all respondents.

4. Wording Questions • Example • In the past 12 months, how many times you have seen or talked with medical doctor about your health? (Include visits to psychiatrists, ophthalmologists, and any other professional with medical degree)

5. Wording Questions • Problem • With this procedure breaks the principle of having all respondents answer the same question and have the same definition. If some respondent are given definitions that others lack, respondents are answering different questions

6. Wording Questions • Principle 3c: The time period referred to by a question should be unambiguous. Question about feelings or behaviors must refer to period time. • Example How often do you feel tired during the day- always, usually, some times ,rarely, or never

7. Wording Questions • Example How often do you feel tired during the day- always, usually, some times ,rarely, or never ? Are you able to run half a mile without stopping? How many drinks do you usually have on days when you drink any alcoholic beverages at all?

8. Wording Questions • Problem • Assuming the stability over the time period • Fail to specify reference period.

9. Wording Questions • Principle 3d: If what is to be covered is too complex to be included in a single question, ask multiple questions.

10. Wording Questions • Principle 4: If survey is to be interviewer administrated, wording of the questions must constitute a complete and adequate script such that , when interviewers read the question as worded, respondent will be fully prepared to answer the question.

11. Wording Questions • Note • Wording issues are different for question that are self administered than when interviewers are reading the questions.

12. Wording Questions • Principle 4a: if definition are to be given, they should be given before the question itself is asked.

13. Wording Questions • Example : Bad: How many days in the past 7 days have you done any exercise? When you consider exercise a on sure to include walking work around the house, or work on a job , if you think they constituted exercise

14. Wording Questions • Example : Better: The next question is going to ask you about how often you have engaged in exercise . We want you to include walking work around the house, or work on a job , if you think they constituted exercise How many days in the past 7 days have you done any exercise?

15. Wording Questions • Principle 4b: A question should end with the question itself. If there are response alternatives , they constitute the final part of the question

16. Wording Questions • Example • Bad: Would you say that you are very likely , fairly likely or not likely to move out of this house in the next year? • (forget the question or the alternative answers) • Better: In the coming year, how likely are you to move to another house? Would you say very likely, fairly likely, or not very likely? (Likely to interrupt before the alternative answers)

17. Wording Questions • Example • Better: which of these categories best describe how likely you think your are to move in the next year: very likely, fairly likely, or not very likely?

18. Wording Questions • Example • Bad: Please tell me whether you consider each of the following to be big problem, a small problem, or no problem at all. • Pain in your bones and joints • Difficulty berating • Any other health problem • (no question , unprepared respondent to answer)

19. Wording Questions • Example • Better: How much of the problem do you consider Pain in your bones and joints to be big problem, a small problem, or no problem at all? • How much of the problem do you consider Difficulty berating to be big problem, a small problem, or no problem at all? And so on

20. Wording Questions • Example • Better: How much of the problem do you consider Any other health problem to be big problem, a small problem, or no problem at all? • (does not constitute a viable question)

21. Wording Questions • Example • A: Is there any other health problem that affects you? • B: Do you consider (Answer to Question A)tobe big problem, a small problem, or no problem at all?

22. Questions