A note on sample size calculation in bioequivalence trials.

Based on fundamental pharmacokinetic relationships, a multiplicative model is commonly used in bioequivalence trials. With regard to the parametric analysis, this implies the assumption of a lognormal distribution. Statistical methods for sample size calculation has been consolidated over the last years. Recently, methods for sample size calculation in the additive model, i.e., under normality assumption, were presented. Hence, these methods are reviewed from a statistical and regulatory point of view.