Online Program Home
My Program

Abstract Details

Activity Number: 500
Type: Contributed
Date/Time: Wednesday, August 3, 2016 : 8:30 AM to 10:20 AM
Sponsor: Biopharmaceutical Section
Abstract #320099
Title: Improved Group Sequential Clinical Trial Designs with Multiple Co-Primary Endpoints
Author(s): Koko Asakura* and Toshimitsu Hamasaki and Franz Koenig and Martin Posch
Companies: National Cerebral and Cardiovascular Center and National Cerebral and Cardiovascular Center and Medical University of Vienna and Medical University of Vienna
Keywords: Alpha-allocation ; Average sample number ; Group sequential designs ; Maximum sample size ; Multiple co-primary endpoints ; Conjunctive power
Abstract:

We derive improved group sequential clinical trial designs comparing two interventions in two co-primary outcomes to evaluate if an experimental treatment is superior to a control on both outcomes ("multiple co-primary endpoints"). Based on the closed testing principle we derive group sequential boundaries that are tailored to the applied stopping rules. We consider stopping rules that stop testing an endpoint as soon as a rejection is occurred (as in settings where measuring the endpoint is invasive or very costly) or requiring that the null hypothesis of all endpoints are rejected at the same stage (to base the test decision on all data collected). Based on the strategy to re-allocate the significance level from the rejected hypothesis for one endpoint to not-yet-rejected hypothesis for the other endpoint we assess the conjunctive power, Type I error rate and sample sizes (maximum sample sizes and average sample numbers). We give examples to illustrate the alpha-reallocation procedures and provide guidance on their use in clinical trials with multiple co-primary endpoints.


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

Back to the full JSM 2016 program

 
 
Copyright © American Statistical Association