Group Sequential and Adaptive Clinical Trial Design

Speaker: Scott Emerson, M.D., Ph.D., Professor of Biostatistics, University of Washington

Presented February 10, 2004

Click here to listen to the archived Web cast.

Downloads

• Presentation Materials by Scott Emerson
• Evaluation of Group Sequential Trials, S. Emerson, J. Kittleson and D. Gillen, 2003
• Monitoring Clinical Trials Through Constrained Boundaries, B. Burington and S. Emerson, 2003
• Coarsened Bayes Inference, K. Koprowicz, S. Emerson, and P. Hoff, 2003
• Information Growth with Weighted Logrank Statistics, D. Gillen and S. Emerson, 2003
• S+Seqtrial: An S-PLUS module for designing, monitoring, and analyzing clinical trials using group sequential methods.

Abstract
Group sequential stopping rules are often used as guidelines in the monitoring of clinical trials in order to address the ethical and efficiency issues inherent in human testing of a new treatment or preventive agent for disease. Such stopping rules have been proposed based on a variety of different criteria, both scientific (e.g., estimates of treatment effect) and statistical (e.g., frequentist type I error, Bayesian posterior probabilities, stochastic curtailment). It is easily shown, however, that a stopping rule based on one of those criteria induces a stopping rule on all other criteria. Thus the basis used to initially define a stopping rule is relatively unimportant so long as the operating characteristics of the stopping rule are fully investigated.

In recent years, a number of authors have proposed adaptive methods of choosing a stopping rule. These methods generally come at the price of statistical efficiency and precision in estimating treatment effects. Fortunately, there is little reason to have to use such adaptive methods, when one is able to fully evaluate the behavior of a nonadaptive stopping rule.

In this seminar, we provide an overview of group sequential clinical trial design and monitoring/analysis. We also compare group sequential and adaptive designs and briefly illustrate some of the loss of precision that arises with adaptive designs. A focal point of the the presentation is an explanation of how the operating characteristics of a particular stopping rule can be evaluated in order to ensure that the selected clinical trial design satisfies the constraints imposed by the many different disciplines represented by the clinical trial collaborators.