Abstract:
|
Many clinical trials aim at multiple study objectives and therefore adequate multiple test procedures should be used to control the family-wise error rate. For many confirmatory trials, Groups sequential trials are often designed to have the opportunity to stop the trial earlier. Here we consider the situation of testing multiple endpoints in a group-sequential clinical trial. Several commonly used procedures will be reviewed and compared, and new strategy is proposed; these procedures have been evaluated by type I errors and powers.
|