What is it about?

In prevalence research, surveys often employ closed questions, where respondents answer with a simple “yes” or “no” regarding specific behaviors within a defined time frame (e.g., “Did you take sleeping pills in the last month”). However, the prevalence obtained through such questions does not provide insights into the frequency of the target behavior. We propose an innovative method to estimate this frequency based on closed questions and did test it by surveying students about their day-to-day behaviors, yielding promising results.

Featured Image

Why is it important?

Due to their simplicity and clarity, prevalence estimates play a crucial role in research, media reporting, and other contexts. For instance, a headline stating “16% of the population take sleeping pills” is easily understood. However, traditional questioning methods only reveal how many people engaged in a particular behavior during a specific period (e.g., the past month). This limited information fails to capture the rate at which the behavior occurs and excludes individuals who engage in the behavior less frequently than the given time frame. Our proposed model addresses these limitations of classical prevalence research methods.

Perspectives

Though this study falls under the category of “basic research,” we find our approach promising and valuable to prevalence research, primarily because of its simplicity and applicability. The model can be utilized across various fields and applications, leading to improved prevalence estimation and a better understanding of behavioral frequencies.

Benedikt Iberl

Read the Original

This page is a summary of: On estimating the frequency of a target behavior from time-constrained yes/no survey questions: A parametric approach based on the Poisson process., Psychological Methods, July 2023, American Psychological Association (APA),
DOI: 10.1037/met0000588.
You can read the full text:

Read

Contributors

The following have contributed to this page