ROBUST BAYESIAN METHODS FOR MONITORING CLINICAL-TRIALS

Bayesian methods for the analysis of clinical trials data have receive d increasing attention recently as they offer an approach for dealing with difficult problems that arise in practice. A major criticism of t he Bayesian approach, however, has focused on the need to specify a si ngle, often subjective, prior distribution for the parameters of inter est. In an attempt to address this criticism, we describe methods for assessing the robustness of the posterior distribution to the specific ation of the prior. The robust Bayesian approach to data analysis repl aces the prior distribution with a class of prior distributions and in vestigates how the inferences might change as the prior varies over th is class. The purpose of this paper is to illustrate the application o f robust Bayesian methods to the analysis of clinical trials data. Usi ng two examples of clinical trials taken from the literature, we illus trate how to use these methods to help a data monitoring committee dec ide whether or not to stop a trial early.