Home > Questionnaire construction
__NOTOC__Questionnaires are frequently used in quantitative marketing research and social research in general. They are a valuable method of collecting a wide range of information from a large number of respondents. Good questionnaire construction is critical to the success of a survey. Inappropriate questions, incorrect ordering of questions, incorrect scaling, or bad questionnaire format can make the survey valueless. A useful method for checking a questionnaire for problems is to pretest it. This usually involves giving it to a small sample of respondents, then interviewing the respondents to get their impressions and to confirm that the questions accurately captured their opinions.
1 Questionnaire construction issues
- The wording must be kept simple : no technical or specialized words. Use short sentences. Writing style should be conversational, yet concise and accurate.
- The meaning should be clear. Avoid ambiguous words and equivocal sentence structures. Avoid double negatives. Even single negatives should be reworded as positives.
- Avoid biasing the responses. A biased question or questionnaire encourages respondents to answer one way rather than another. Avoid “loaded” questions.
- Ask one question at a time. Avoid complex questions. If more than one question is hidden in a survey question, the researcher will not know which one the respondent is answering.
- Avoid personal or intimate questions. Most people will not answer them.
- Consider the respondent’s frame of reference. What is their background, and how will this effect their interpretation of the questions? Do respondents have enough information or expertise to answer the question?
- Ask yourself if each question is really necessary. Unneeded questions are an expense to the researcher and an unwelcome imposition on the respondents. To answer this question, you must consider the objective(s) of the research.
- Ask yourself what type of data analysis techniques are available for various kinds of questions. Will the question provide you with the statistical analysis that you want?
- What type of content will responses to the question yield? Will the question responses provide facts, beliefs, feelings, descriptions of past behavior, or standards of action?
- What type of scale, index, or typology should be used?
- How should the questions be presented on the page (or computer screen)? How much white space? How many colours? Do you use pictures, charts, or other graphics? It should be colourful enough to gain and maintain respondent interest, but not so graphic as to distract from the of the questions.
- Should questions be open-ended or should respondents’ answers be limited to a fixed set of responses?
- What order should the questions be in? Is there a “natural” grouping to the questions? Will previous questions bias later questions?
- Should the questions be numbered? Generally this is a good idea.
- Are possible responses mutually exclusive? The respondent should not find themselves in more than one category, for example in both the “married” category and the “not living with spouse” category. Categories should not overlap.
- Is the list of possible question responses inclusive? The respondent should not find themselves with no category that fits their situation.
- Is the questionnaire going to be administered by research staff, or will it be self-administered by the respondents. Self administered questionnaires must give clear, detailed instructions.
2 Types of questions
- Contingency questions - A question that is answered only if the respondent gives a particular response to a previous question. This avoids asking questions of people that do not apply to them (for example, asking men if they have ever been pregnant).
- Matrix questions - Identical response categories are assigned to multiple questions. The questions are placed one under the other, forming a matrix with response categories along the top and a list of questions down the side. This is an efficient use of page space and respondents’ time.
- Scaled questions - Responses are graded on a continuum (example : rate the appearance of the product on a scale from 1 to 10, with 10 being the most preferred appearance). Examples of types of scales include the Likert scale, semantic differential scale , and rank-order scale (See scale for a complete list of scaling techniques.).
- Closed ended questions - Respondents’ answers are limited to a fixed set of responses. Most scales are closed ended. Other types of closed ended questions include:
- Dichotomous questions - The respondent answers with a “yes” or a “no”.
- Multiple choice - The respondent has several option from which to choose.
- Open ended questions - No options or predefined categories are suggested. The respondent supplies their own answer without being constrained by a fixed set of possible responses. Examples of types of open ended questions include:
- Completely unstructured - For example, “What is your opinion of questionnaires?”
- Word association - Words are presented and the respondent mentions the first word that comes to mind.
- Sentence completion - Respondents complete an incomplete sentence. For example, “The most important consideration in my decision to buy a new house is . . .”
- Story completion - Respondents complete an incomplete story.
- Picture completion - Respondents fill in an empty conversation balloon.
- Thematic apperception test - Respondents explain a picture or make up a story about what they think is happening in the picture
