184-30: Empirical Power for Higher-Order Crossover Designs in Comparative Bioavailability Clinical Trials

A standard 2x2 crossover design has been widely used in drug clinical trials, but it is not optimal because of some undesirable statistical properties such as the low power to test carry-ov er effect. Higher-order crossov er designs address this defficiency and, theref ore, have drawn more attention recently. Howev er, exact power calculation of higher-order crossov er designs poses difficulity f or users. It requires sophisticated numerical integration, and it is not available in statistical software packages. This paper presents a SAS Macro to compute the empirical power for higher-order designs in comparative bioavailability clinical trials. The power curve and tables for higher-order crossover design with 2 sequences and 3 periods are presented.