Jump to content
Sun 7th 09:00 - 13:00

Pre-Conference Workshop 1 – Learning Bayesian Methods and Adaptive Designs: Concepts, Tools, and Applications

Workshop Presenters

Jack Lee, Ph.D. Department of Biostatistics, University of Texas MD Anderson Cancer Center, USA
James Wason, Ph.D. MRC Biostatistics Unit, University of Cambridge, UK

Description of Workshop

This workshop will provide an overview of Bayesian theory and concepts in the context of clinical trials. We will cover a variety of standard statistical models as well as recently developed Bayesian methods for the design and conduct of adaptive clinical trials. Emphasis will be on practical applications, with the workshop structured around a series of illustrative examples. Additionally, hands-on Bayesian computational tools including WinBUGS, OpenBUGS, BRugs, R, and SAS PROC MCMC, etc. will be introduced as well as easy-to-use Shiny applications and downloadable standalone programs to illustrate Bayesian computation and inference making.

In addition, the applications of Bayesian methods to designing adaptive clinical trials will be illustrated. Topics include Bayesian toxicity and efficacy monitoring, interim analysis, posterior probability and predictive probability designs for evaluating efficacy, outcome-adaptive randomization, hierarchical models, adaptive biomarker identification and validation, platform designs, and multi-arm, multi-stage designs, etc.  Bayesian adaptive designs allow flexibility in clinical trial conduct, increase study efficiency, enhance clinical trial ethics by treating more patients with more effective treatments, and can still preserve frequentist operating characteristics by controlling type I and type II error rates. Practical considerations for conducting adaptive designs and lessons learned from real trial examples will be given.

Target Audience
Clinical biostatisticians working on the design and analysis of clinical trials. Clinical trialists with interest in learning Bayesian statistics and adaptive designs. A good understanding on elementary statistics and some familiarity with computing tools will help but not required.