How large should a pilot study be?

Abstract

Background: Pilot studies are used to identify unforeseen problems or flaws in the procedures and instruments to be used in a subsequent larger trial. But how many participants have to be included in a pilot study in order to be reasonably sure that important problems and flaws will be detected? The aim of this paper is to present a method for sample size calculations in pilot studies. Methods: A formula has been worked out to calculate the sample size needed to be able to identify, with a chosen level of confidence, problems that may arise with a given probability. Findings: A simple formula that can be used to calculate the sample size needed for a pilot study. For example, if a problem exists with 5% probability in a potential study participant, the problem will almost certainly be identified (with 95% confidence) in a pilot study including 59 participants. Discussion: This method can be used to determine the necessary sample size so that the problem is likely to be observed at least once during the course of the pilot study.