|
Activity Number:
|
373
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Wednesday, August 1, 2007 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Bayesian Statistical Science
|
| Abstract - #309062 |
|
Title:
|
Constructing Bayesian Trials in a Type I Error--Controlled Regulatory World: The Good, the Bad, and the Ugly
|
|
Author(s):
|
Scott Berry*+
|
|
Companies:
|
Berry Consultants
|
|
Address:
|
3145 Chaco Canyon Drive, College Station, TX, 77845,
|
|
Keywords:
|
Bayesian ; Adaptive Trials ; Medical Devices ; Type I error ; Priors
|
|
Abstract:
|
The use of Bayesian statistics in trial design allows for innovative adaptive designs to be done. Some strengths of the Bayesian approach include using prior information, flexibility in the adaptive sample size, flexibility in randomization probabilities and predictive probabilities. Many regulatory agencies allow and encourage Bayesian and adaptive techniques in clinical trial design, but constrain the Bayesian approach to satisfy frequentist type I error levels. In this talk I discuss the ramifications of these restrictions: some good, some bad, and some ugly!
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2007 program |
