The previous four chapters have provided a summary of questionnaire theory. Hopefully, they have also made a strong case for basing questionnaire design and processing on scientific principles rather than merely on the researcher's common sense. As emphasized in the Introduction, this book has been intended to serve practical purposes and therefore in this concluding section I will draw up a checklist of what I consider the most important points and recommendations for every phase of the questionnaire survey. Good luck with your future questionnaires!
1. Only in exceptional cases should a questionnaire be more than 4 pages long and take more than 30 minutes to complete; if access to the participants is restricted to a certain amount of time, set the maximum length of the questionnaire with the slowest readers in mind so that everybody can finish within the given period.
2. When deciding on the questionnaire content, start by generating a theoretically driven list of the main areas to be covered.
3. Avoid the use of single-item variables; instead, include minimum 3-4 items addressing every content area.
4. Avoid truly open-ended questions that require lengthy answers.
5. Keep the number of items that are seeking confidential information to the minimum.
6. Be careful about how you formulate sensitive items (for specific guidelines, see Section 2.6.3).
7. Try and make the starter questions particularly involving.
8. Make sure that the questionnaire has a clear, logical, and well-marked structure.
9. Personal/factual questions about the respondent should go to the end.
10. Open-ended questions are the least intrusive if they are toward the end.
11. When writing items, observe the following:
• The best items are often the ones that sound as if they had been said by someone.
• Short items written in simple and natural language are good items.
• Avoid ambiguous, loaded, or difficult words; technical terms; negative constructions; and double-barreled questions.
• Avoid items that are likely to be answered the same way by most people.
• Include items that concern both positive and negative aspects of the target.
12. Strive for an attractive and professional design for the questionnaire; this typically involves:
• economical use of space with full but not overcrowded pages,
• an orderly layout that utilizes various typefaces and highlighting options, and appropriate sequence marking (of sections and items),
13. In the initial (general) instructions cover the following points:
• the topic and importance of the study,
• the sponsoring organization,
• point out that there are no right or wrong answers and request honest responses,
• promise confidentiality,
• thank the participants.
14. In the specific instructions to the tasks exemplify (rather than merely explain) how to answer the questions.
15. Thank the participants again at the end of the questionnaire.
16. Always pilot your questionnaire in a systematic manner and submit the items to item analysis (cf. Section 2.9).
Administering the questionnaire
17. Make the participant sample as representative of the total population you are investigating as possible (cf. Section 3.1.1).
18. Make the sample size large enough to allow for statistically significant results (cf. Section 3.1.2).
19. Beware of participant self-selection (cf. Section 3.1.3).
20. With postal administration:
• Formulate the cover letter very carefully (for a list of points to be covered, see Section 3.2.1).
• Print the return address on the questionnaire as well.
• About 2Vi weeks after the original mailing send a follow-up letter, and in another 10 days' time send another one.
• Apply various strategies to increase the return rate (for a list, see Section 3.2.1).
21. With one-to-one administration, make sure that you brief the questionnaire administrator well and consider giving him/her a cue card with the main points to cover when handing out the questionnaires.
22. To increase the quality and quantity of questionnaire response, apply the following strategies:
• Provide advance notice.
• Win the support of the various authority figures.
• Try to arrange some respectable institutional sponsorship for your survey.
• The administrator's overall conduct should be friendly and professional, and he/she should exhibit keen involvement and an obvious interest in the project.
• 'Sell' the survey by communicating well its purpose and significance.
• Emphasize confidentiality.
• Promise feedback on the results for those who are interested (and then remember to provide it...).
23. Observe the various ethical principles and regulations very closely
(cf. Section 3.4.1) and obtain the required 'human subjects' approval.
Processing questionnaire data
24. As soon as you have received the completed questionnaires, mark each with a unique identification code.
25. Record every important step you take during the processing of the data in a 'Research Logbook.'
26. Prepare a coding frame for each item and record these in a codebook.
27. Always prepare a backup of the data files. Do it now!
28. Submit your data to 'data cleaning procedures' before starting the analyses (cf. Section 4.3.1).
29. Consider the way you handle missing data very carefully.
30. Reverse the scoring of negatively worded items before starting the analyses (cf. Section 4.3.2).
31. Consider standardizing the data before starting the analyses (cf. Section 4.3.2).
32. Start the analyses of your questionnaire data by reducing the number of variables through computing multi-item scales.
33. Compute internal consistency reliability coefficients (Cronbach Alphas) for each multi-item scale.
34. Numerical questionnaire data are typically processed by means of statistical procedures; for most purposes you will need inferential statistics accompanied by indices of statistical significance (cf. Section 4.3.6).
35. Process open-ended questions by means of some systematic content analysis.
36. Exercise great caution when generalizing your results.
37. Make sure that you include all the necessary technical information about your survey in your research report (for a checklist, see Section 4.6.2).
38. Make use of charts/diagrams, schematic representations, and tables as much as possible when reporting your results.
39. Consider complementing your questionnaire data with information coming from other sources.
Was this article helpful?
There are people all over the world trying to find ways to make money online. From stay at home moms looking to make a few extra dollars to college students and entrepreneurs, the allure of making your own hours and working from home or from the local coffee shop is very appealing.