Adaptive sample size calculations in group sequential trials

A method for group sequential trials that is based on the inverse normal me thod for combining the results of the separate stages is proposed. Without exaggerating the Type I error rate, this method enables data-driven sample size reassessments during the course of the study. It uses the stopping bou ndaries of the classical group sequential tests. Furthermore, exact test pr ocedures may be derived for a wide range of applications. The procedure is compared with the classical designs in terms of power and expected sample s ize.