The use of pilot study data in the estimation od sample size

Abstract

In the two sample binomial case, one approach to the estimation of sample size is to conduct a pilot study and assume that the observed proportion in the pilot study have no sampling error and are in fact true population parameter which can be used directly in standard sample size formulas. This approach has conceptual difficultie swhen such a pilot study is small since there is typically considerable error in the observed proportions. In this paper; we propose an lternative method which takes into account the sampling error in pilot study data in the estimation of sample size for a larger study. Tables are provided comparing these two methods and it is shown that the former deterministic method may provide a grossly inaccurate estímate of the appropriate sample size for alarger study, partlcularly for small pilot studies.