Online Program Home
My Program

Abstract Details

Activity Number: 612
Type: Contributed
Date/Time: Wednesday, August 3, 2016 : 2:00 PM to 3:50 PM
Sponsor: Biopharmaceutical Section
Abstract #318679 View Presentation
Title: Multi-Arm Group Sequential Designs with Simultaneous Stopping Rule
Author(s): Susanne Urach* and Martin Posch
Companies: Medical University of Vienna and Medical University of Vienna
Keywords: Multi-arm multi-stage designs ; multiple treatment arms ; early stopping
Abstract:

Multi-arm group sequential clinical trials are efficient designs to compare multiple treatments to a control. They stop randomization to a treatment arm already in an interim analysis if a significant treatment effect in that arm is observed. Only the remaining treatment arms are continued to the next stage. We consider a variant of such designs where a simultaneous stopping rule is applied and the whole trial is stopped as soon as the null hypothesis of no treatment effect for any of the arms can be rejected. While the critical boundaries of the classical multi-arm trials control the type I error rate also under the simultaneous stopping rule, the corresponding test becomes strictly conservative. For the comparison of two experimental treatments we derive improved stopping boundaries that exhaust the type I error rate for such designs and optimize these boundaries to minimize the average sample number. In addition, we compare the operating characteristics of the improved trial designs and standard multi-arm group sequential designs. The procedure is illustrated with a clinical trial in systemic sclerosis.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2016 program

 
 
Copyright © American Statistical Association