JSM 2012 Home

JSM 2012 Online Program

The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.

Online Program Home

Abstract Details

Activity Number: 522
Type: Contributed
Date/Time: Wednesday, August 1, 2012 : 10:30 AM to 12:20 PM
Sponsor: Biopharmaceutical Section
Abstract - #305875
Title: A General Approach for Estimating Stopping Probabilities of Large Group Sequential Trials in Life-Threatening Conditions Monitoring Binary Efficacy and Safety Outcomes
Author(s): Yanqiu Weng*+ and Wenle Zhao and Yuko Palesch
Companies: Medical University of South Carolina and Medical University of South Carolina and Medical University of South Carolina
Address: 135 Cannon Street Suite 303, Charleston, SC, 29425, United States
Keywords: Data and Safety Monitoring Committee ; efficacy ; group sequential design ; power ; safety ; type I error

In large confirmatory trials for life-threatening conditions, some adverse events are not rare or unexpected, and can be formally monitored under a statistical guideline. However, it is unknown how much safety monitoring would impact the error probabilities for efficacy analyses. On the other side, the decision making from Data Safety Monitoring Committees (DSMC) on early stopping a study is flexible, but most methods and available software for alpha spending and sample size calculation are based on the assumption that DSMCs strictly complies with statistical guidelines, which is not realistic. We develop a new approach to estimate the stopping probabilities for a bivariate efficacy-safety response in large group sequential trials. In addition to handling the multiplicity issue for multiple outcomes, the new approach is able to provide power estimations under various assumptions on data monitoring practices. The method is verified by Monte Carlo simulation and is demonstrated based on a real stroke trial. The findings from this study suggest that formal safety monitoring in life-threatening conditions could have a dramatic impact on error probabilities for efficacy analyses.

The address information is for the authors that have a + after their name.
Authors who are presenting talks have a * after their name.

Back to the full JSM 2012 program

2012 JSM Online Program Home

For information, contact jsm@amstat.org or phone (888) 231-3473.

If you have questions about the Continuing Education program, please contact the Education Department.