Controlled Bayesian Optimal Designs for Dose-Response Studies

• Activity Number: 378
• Type: Contributed
• Date/Time: Wednesday, August 1, 2007 : 8:30 AM to 10:20 AM
• Sponsor: Biopharmaceutical Section
• Author(s): Wei Zhu*+ and Jiaqiao Hu and Weng-Kee Wong
• Companies: State University of New York at Stony Brook and State University of New York at Stony Brook and University of California, Los Angeles
• Keywords: Bayesian multiple-objective optimal design ; dose response study ; logit model

Abstract

Dose-response studies are routinely conducted to determine viable dose levels for newly developed therapeutic drugs. Due to safety, efficacy, and experimental design considerations, practical constraints are often imposed on (1) dose range, (2) dose levels, (3) dose numbers, (4) dose proportions, and (5) potential missing observations. We propose the controlled Bayesian multiple-objective optimal designs satisfying one or more of these practical constraints, for dose response studies. The resulting controlled optimal designs satisfying these realistic constraints can be readily adopted by the pharmaceutical researchers for optimal estimation of the parameters of interest such as the median effective dose level or the threshold dose level. We demonstrate our results and methodology through the logit dose response model.