1 / 79

Class 8 Pretesting Measures and Creating a Questionnaire November 12, 2009

Class 8 Pretesting Measures and Creating a Questionnaire November 12, 2009. Anita L. Stewart Institute for Health & Aging University of California, San Francisco. Overview of Class 8. Choosing best measure(s) for pretesting Creating a questionnaire Pretesting measures - types of pretests

Download Presentation

Class 8 Pretesting Measures and Creating a Questionnaire November 12, 2009

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Class 8 Pretesting Measures and Creating a QuestionnaireNovember 12, 2009 Anita L. Stewart Institute for Health & Aging University of California, San Francisco

  2. Overview of Class 8 • Choosing best measure(s) for pretesting • Creating a questionnaire • Pretesting measures - types of pretests • Cognitive interviewing • Designing your own pretest

  3. Process of Selecting Good Measures for Your Studies Define concept (variable) Identify potential measures Review measures’ properties --conceptual adequacy --psychometric adequacy Pretest best 1-2 measures Select final measure

  4. Select Best Candidate Measures to Pretest • Select best measures for all concepts in your conceptual framework • Pretest measures you plan to use • Pretest 2 measures of key concepts if possible so you can choose the best one

  5. Strategies for Selecting Best Measure of “Unidimensional” Concept • Select existing measure in its entirety • Select two existing measures • Have a choice later based on psychometric results

  6. Strategies for Selecting Best Measure of “Multidimensional” Concept • Select existing instrument in its entirety • Select subscales of only relevant domains from existing instruments • those that meet your needs • Supplement either of the above with subscales from other measures

  7. What if There is No “Best” Measure? • For priority concepts with inadequate measure, select the one that is the closest in your review • Use pretest or other qualitative studies as basis to adapt or modify • For priority concepts with no measure that meets your needs, may require development of new measure

  8. Documenting Measures in Your Study • Handout – sample guide to measures used in questionnaires • Before you forget – • Summarizes source of all measures to be administered in your study

  9. Overview of Class 8 • Choosing best measure(s) for pretesting • Creating a questionnaire • Pretesting measures - types of pretests • Cognitive interviewing • Designing your own pretest

  10. Considerations in Creating a Questionnaire • Introduction • Statement of confidentiality • Length • Sections, section headings to break it up • Order of questions, measures • Formatting • Conclusion

  11. Introduction: Inform respondent … • Purpose of overall study and of this questionnaire • Who is conducting the study • Topics included in questionnaire • Expected time to complete • Assurance that participation is voluntary, can skip any questions • Specific instructions for completing

  12. Statement of Confidentiality • Inform respondents of extent to which their answers are protected • if there are risks to confidentiality, state them • Can use section from consent form pertaining to survey data

  13. Sample Statement of Confidentiality • “All information that would permit identification of individuals will be regarded as strictly confidential, will be used for purposes of evaluating the study, and will not be disclosed or released for any other purposes without prior consent, except as required by law.”

  14. Statement of Confidentiality (cont.) • Note that this is a very high reading level • Would need to simplify for lower SES group • “All information about you will be kept as confidential as possible. Your name will not be used in any published reports about this study.”

  15. Length of Questionnaire • Acceptable length depends on: • Interest of respondents in topic area • Health • Free time of respondents

  16. Create Sections of Questionnaire • Break up with sections, grouped by topic (minimizes psychological burden) • Introduce new topics with • Phrases - “the next questions are about how you’ve been feeling” • Simple section headings, e.g., How You’ve Been Feeling

  17. Question Order • Order can affect willingness to complete survey • Begin with general questions • Easy, non-threatening, interesting, related to purpose of study • Proceed with more specific questions, personal and sensitive questions • Conclude with demographics (least interesting, sensitive)

  18. Indicate How to Respond • Give specific instructions for answering questions, e.g., • Circle all that apply • Circle one number • Check the box that best represents howyou feel • If no instructions, subjects will have to figure out what to do and may not do it correctly

  19. Formatting Self-Administered Questionnaires • Make the tasks of reading questions, following instructions, and recording answers as easy as possible for respondents • Clear instructions for indicating their answer • Easy to track separate questions

  20. Principles of Formatting • Create a lot of space on page • Use very light background for best contrast • Minimize use of color as background • Number all questions (unique number for each one helps data entry) • Allow sufficient space to write answers to open-ended questions • Special issues for older adults: • Larger font size (14) • Higher contrast (black on white)

  21. Types of Formats: Horizontal How would you rate your health in general? (check one box)  Excellent  Good  Fair  Poor (Easy to get confused)

  22. Types of Formats: Respondent Writes Response Choice For each question, write in one of the following numbers: 1 = poor 2 = fair 3 = good 4 = excellent ___ 1. How would you rate the availability of medical information by phone? ___ 2. How would you rate the length of time spent waiting at the office to see a provider?

  23. Types of Formats: Vertical During the past 4 weeks, did your healthlimit you in walking one block..

  24. Types of Formats: Matrix

  25. Types of Formats: Matrix with Boxes

  26. Conclude Questionnaire • Add a brief thank you for completing the questionnaire (for their time and effort) • If questionnaire is to be mailed back, include instructions for mailing • Always include a pre-stamped, preaddressed return envelope

  27. Resources for Creating Questionnaires • Mullin et al article on formatting principles • Handout: formatting tips for using WORD • See sample questionnaires in class • (sample formats)

  28. Overview of Class 8 • Choosing best measure(s) for pretesting • Creating a questionnaire • Pretesting measures - types of pretests • Cognitive interviewing • Designing your own pretest

  29. Pretest in Target Population • Pretesting essential for measures being applied to any new population group • Especially priority measures (e.g., outcomes) • Pretest is to identify: • problems with procedures • method of administration, respondent burden • problems with questions • Item stems, response choices, and instructions

  30. Types of Pretests • General debriefing pretest (N=10) • Large pretest (N=100) • test measurement properties prior to major study • In-depth cognitive interviewing pretest

  31. Types of Pretests • General debriefing pretest (N=10) • Large pretest (N=100) • test measurement properties prior to major study • In-depth cognitive interviewing

  32. General Debriefing Pretest • Goal • Identify problems with the procedures • Estimate time needed to complete instrument • Identify serious problems with items • Procedures • Subjects answer entire questionnaire • At end, debrief • Close to true task

  33. Sample Debriefing Questions After Administration of Survey.. Ask respondents: • Were any questions confusing? • Which words were hard to understand? • Which questions were difficult to answer? caused distress? • Was questionnaire too long? • Were instructions confusing?

  34. “Questionnaire” Asking Opinions About another Questionnaire/Survey • Six questions about burden of a survey • Questionnaire length • Ease of answering questionnaire • Negative affect burden (4 items) • Feeling embarrassed, upset, annoyed, uncomfortable M Zimmerman et al., Med Care, 1994;32:603-608

  35. 4-item Negative Affect Burden Scale • How much were you annoyed by being asked these questions? • How much were you embarrassed by being asked these questions? • How much did it upset you to be asked these questions? • How uncomfortable did it make you feel to be asked these questions? • Responses: very much, somewhat, a little, not at all Zimmerman M et al.1994

  36. Problems with General Pretests • Respondents… • often don’t understand the task. • don’t want to appear as if they didn’t understand • have a hard time telling you anything was wrong • easier to say everything was fine

  37. Types of Pretests • General debriefing pretest (N=10) • Large pretest (N=100) • test measurement properties prior to major study • In-depth cognitive interviewing

  38. Large Pretest – N=100 • Test psychometric properties and procedures for large-scale administration • Administer surveys • Examine item distributions, missing data • Calculate internal-consistency reliability • Conduct some preliminary validity studies • Only large-scale studies have this luxury

  39. Large Pretest of 4 Patient Satisfaction with Hospital Care Measures (N=2,850) • Compared 4 questionnaires on • Response rates, missing data, completion time • 10 evaluation items at end of questionnaire (1-5 agree-disagree scale) • Clarity of questions, ease of finding an answer, questions about unimportant issues, ease of completion, too long, layout confusing, lacked important questions TV Perneger et al., Med Care 2003;41:1343-1352

  40. Medical Outcomes Study Measures • On long-form measures, conducted 9 full-scale pilot studies over a 1-year period • Physical functioning, health perceptions, energy/fatigue, sleep, role functioning, pain, symptoms, family functioning, sexual functioning • Samples ranged from 50-100 each Stewart AL and Ware JE, Measuring Functioning and Well-Being, 1992, p. 72..

  41. Types of Pretests • General debriefing pretest (N=10) • Large pretest (N=100) • test measurement properties prior to major study • In-depth cognitive interviewing pretest (N=5-10 each group)

  42. Overview of Class 8 • Choosing best measure(s) for pretesting • Creating a questionnaire • Pretesting measures - types of pretests • Cognitive interviewing • Designing your own pretest

  43. In-Depth Cognitive Interviews • Derived from social and cognitive psychology to explore processes respondents use to answer survey questions • Goal: understand thought processes used to answer questions • Can help write/adapt questions

  44. Types of Problems with Questions or Response Choices • Are all words/phrases understood as intended? • Are questions interpreted similarly by all respondents? • Are some questions not answered? • Are any questions offensive or irrelevant? • Does each closed-ended question have an answer that applies to each respondent? • Are the response choices adequate?

  45. Cognitive Interviews Examine 4 Steps in Answering Questions • Comprehend question (as intended) • Retrieve information - various strategies used to recall information • Judgment formation - calculate the correct response • Response - decide what to report Sudman S et al., Thinking About Answers, Jossey-Bass, San Francisco, 1996

  46. Comprehend Questions as Intended • Bulk of cognitive interview pretests assess whether your items are interpreted by respondents as you intended

  47. Retrieve Information • Information needed to answer the question must be retrieved from memory • Episodic data – stored in detail • Schemas – generalizations about events • Frequent, routine events more likely to be stored as “schema” with no detail

  48. Example of Retrieval Schema • People with chronic conditions and a lot of doctor visits tend to have “generic” memories of these visits • Multiple visits blurred together • Could describe a typical visit but not any visit in particular • Hard to recall how many visits

  49. Judgment Formation • Involves using the recalled information to estimate frequency of an event, or to decide whether one agrees or disagrees with a statement • Cues taken from the item response choices

  50. Response • After respondent has judged what the best answer is, decides how to respond • Accurately? • To improve social desirability? • To minimize embarrassment?

More Related