Estimating sample size in clinical studies: basic methodological principles.

Abstract

In order to be valid, clinical studies must be methodologically rigorous. The internal validity of a study is of crucial importance: a study is valid if its results are an unbiased estimation of the true result. In this case, the validity is internal because it refers to the group of patients under study and not necessarily different ones (external validity or applicability). Internal validity in clinical research is achieved through rigorous design, data collection and appropriate analysis, and is threatened by bias (systematic errors) or chance (random variation of the phenomena under study). Regardless of the type of study (analytic, descriptive, etc.), the characteristics of its sample are fundamental for the validity of the results. The sampling methods are crucial if the study patients are to be representative of the population to which one desires to extrapolate the results. One of the most fundamental characteristics of a sample is its size. Even the best executed study may fail to answer the research question if the sample size is too small. On the other hand, a study with too large a sample is harder to conduct and more costly. The goal of planning the sample size is to estimate the appropriate number of research subjects for the study. In this paper we will present and discuss the methodological principles underlying calculation of sample size: outcomes, type I and II error, alpha and beta, study power and variability.