Many questions in survey research assume regularity of behavior. Read this question and then look at what two respondents thought when they tried to answer it.
Thinking of the past 12 months, how often have you baked a cake?
___ Less than once a month
___ 1 to 3 times a month
___ More than 3 times a month
Sarah: “I bake cakes when there is a birthday party. We’ve had three in my family this year, all in November. Does that mean three times a month?”
Jamie: “I bake one or two cakes every month during the school year. I don’t bake any during the summer. I do pies during the holidays. I am not sure how to answer the question.”
This question assumes that people bake cakes on a regular schedule. But neither of these respondents bakes cakes according to the regular schedule offered by the question. They can’t answer the question, which is why I have this guideline in chapter 7, Make Questions Answerable.
When you are not sure behavior is regular, ask the question in a way that does not assume regularity. Set a time period, such as a week, month, or year, and ask for the number of times the respondent performed the task in that time period.
Improved Question:
Thinking of the past 12 months, about how many times did you, yourself, bake a cake?
____ # times baked cake in past 12 months
This revised question asked about the number of times the respondent baked a cake in the 12-month period and eliminated the idea of regularity of behavior from month to month.
Here is another question that incorrectly assumes regularity of behavior.
Thinking of the past 12 months, how often have you traveled by air?
___ Daily
___ Weekly
___ Monthly
___ A few times
___ Once
___ Never
For many people, air travel does not follow a regular pattern. Here is an improved version of the question:
Thinking of the past 12 months, about how many times have you, yourself, traveled by air?
___ # times traveled by air in past 12 months
Unless you know that a behavior follows a consistent pattern, don’t require respondents to fit their behavior into categories that assume regularity of behavior. When you do qualitative research before designing the survey, find out if the behavior you want to measure follows a consistent pattern, or not.
