A Bayesian Approach for Local Bridging Evaluation and Sample Size Determination in a Multiregional Trial

• Activity Number: 7
• Type: Invited
• Date/Time: Sunday, August 3, 2008 : 2:00 PM to 3:50 PM
• Sponsor: WNAR
• Author(s): Yi-Hau Chen and Ya-Chi Wu and Mey Wang*+
• Companies: Institute of Statistical Science, Academia Sinica and Center for Drug Evaluation, Taiwan and Center for Drug Evaluation, Taiwan
• Keywords: multi-regional trial ; bridging evaluation ; Bayesian approach ; sample size determination

Abstract

A multiregional trial, conducted in more than one region under a common protocol, has been proposed with the desire to allow for global drug development and registration. Further, a multiregional trial allows for bridging evaluation so that global information can be utilized to support the registration of the drug at a given local region. From a statistical point of view, such an "information sharing" purpose can be nicely achieved by appealing to suitable Bayesian analysis. We propose a Bayesian approach for evaluating the drug effectiveness at a local region in a multiregional trial, where the posterior probability that the drug is effective at the local region is used, with the prior information obtained from the global data. A corresponding Bayesian approach for determination of the required sample size for evaluating the drug effectiveness in a local region is also proposed.