3. Overview
A questionnaire is a tool for systematically gathering
information from study participants.
Questionnaires can be designed for self-reporting or as
scripts for interviews.
5. Questionnaire Content
It is often helpful to start with a list of the main
categories of questions to be asked, and then to add
detail about the specific topics to be covered.
6. Questionnaire Content
• The questionnaire must include questions confirming
that participants meet the eligibility criteria for the
study.
• The questionnaire must also be able to accurately
place participants into key categories, such
confirming that all cases in a case-control study meet
the case definition.
• A survey should be neither too short nor too long.
7. Types of Questions
After determining the broad categories of questions and
the specific topics to be addressed in each section, each
question topic should be assigned a specific type of
question.
•Close-ended questions allow a limited number of
possible answers
•Open-ended questions allow participants to give free-
response answers
8. Open-Ended Questions
Open-ended questions allow participants to:
•explain their selections and qualify their responses
•give multiple answers
•provide responses not anticipated by the researcher
However:
•they take longer to ask and answer
•they may result in irrelevant answers
•recoding for statistical analysis is often difficult
9. Close-Ended Questions
Close-ended questions come in a variety of formats,
including:
•Date and time variables
•Numeric variables
•Categorical variables
•Paired-comparison variables
•Rank-order variables
10. Close-Ended Questions
Categorical variables come in a variety of formats:
•Dichotomous variables have only two response options
(like yes/no)
•Ordinal variables are ranked based on an inherent
order
•Nominal variables are have no built-in order
12. Anonymity
• Many questions can be asked in more than one valid
way, and the researcher must decide which question
type is most appropriate and will best protect
participants’ anonymity.
• If a name, an address, a birthdate, or other
information could link a participant to the study, then
there must be a solid plan in place for protecting the
privacy of participants and the confidentiality of the
information they share.
13. Types of Responses
Once the types of questions have been selected, a
decision must be made about the kinds of responses that
are appropriate for the question.
14. Types of Responses
• For numeric responses, the question should state
exactly how specific the answers should be.
• For categorical questions, consider all possible
responses for each question, and include as many as
needed (including, perhaps, “other” and “I do not
know”).
• For ranked questions, decide how many entries to
include on the scale and whether there will be a
neutral option.
16. Wording of Questions
After drafting the questionnaire, check each question for
clarity:
•Does each question ask what it is intended to ask?
•Is the language of each question clear and neutral?
•Will members of the study population understand the
language?
•Is the question sensitive to potential cultural issues
related to language?
17. Wording of Questions
Check to be sure that the responses are carefully
worded:
•Is the choice of response clear?
•For scaled questions, is the rank order clear? (For
example, is it clear that 1 is “strongly disagree” and 5 is
“strongly agree”?)
•For questions with unranked categories, is the order of
possible responses alphabetical or otherwise neutral?
19. Order of Questions
• Many questionnaires start with easy or at least
general questions before moving to more difficult or
sensitive questions.
• The questions should be in an order that flow
naturally from one topic to another, and similar
questions should be grouped.
• Think carefully about how previous questions could
taint the answers to later ones.
20. Layout and Formatting
The layout of the survey instrument will vary depending
on the mechanism of data collection used.
•A self-report survey, either paper-based or computer-
based, may require instructions about how to indicate
answers.
•For an oral survey, the interview script requires an
opening statement, transitions between sections of the
survey, closing sentences, spaces for recording
responses to questions, and other instructions.
23. Validation
A valid questionnaire measures what it was intended to
measure in the population being assessed.
•One way to seek validity is to include survey questions
or modules that are identical to the ones used in
previous research projects, but access to survey
questions is often not possible in the health sciences.
•Pilot testing of the new questionnaire is essential for
the development of a valid and useful tool.
24. Commercial Research Tools
A number of widely used and validated tests, primarily
from the social sciences, are available to researchers as
commercial products.
•Some of these tools are free of charge, but most require
payment for use.
•Some tests provide the instrument for free but require
researchers to pay to have the results scored and
validated against previous users of the survey
instrument.
25. Translation
Translation of the survey instrument into one or more
additional languages may be necessary.
•Check to be sure that the translated version expresses
the same meaning as the original survey.
•Accuracy may require the rephrasing of whole
sentences, not just direct word-for-word translations.
26. Pilot Testing
A pilot test (pretest) of the questionnaire is helpful for
checking content, clarity, layout, timing, and other
factors.
•Volunteers from the target population (but not the
sample population) should be asked to complete the
preliminary survey and provide feedback on it.
•The survey instrument should be revised based on
these observations.
•Several rounds of pilot testing may be required.