Some Statistical Considerations on 2 x k Crossover Designs for Bioequivalence Trial

The Korea Food and Drug Administration(KFDA) recommends the use of a 2 x 2 crossover design to assess the bioequivalence of generic drugs. However, a standard 2 x 2 crossover design for bioequivalence trials is often considered problematic due to ethical and economic issues as highly variable drugs are usually required by large numbers of subjects when designing the trial. To overcome this problem a 2 x 4 crossover design has been a recommended option as per US regulations; in addition, a 2 x 3 crossover design has also recently drawn special attention as an efficient alternative. The current KFDA regulation requires an ANOVA table for every bioequivalence study; however, ANOVA tables of 2 x 4 and 2 x 3 crossover designs have never been published in the literature. This study shows the derivation of tables of analysis of variance for a 2 x 4 cross-over design and a 2 x 3 cross-over design. We also suggest a sample size formulas for 2 x 2, 2 x 4 and 2 x 3 crossover designs to provide information on the selection of efficient designs for highly variable drugs.