|
Activity Number:
|
362
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 6, 2008 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Bayesian Statistical Science
|
| Abstract - #301049 |
|
Title:
|
The Impacts of Misclassification on Bayesian Adaptive Designs
|
|
Author(s):
|
Jo A. Edmonds*+ and John W. Seaman, Jr. and James Stamey
|
|
Companies:
|
The University of Kansas Medical Center and Baylor University and Baylor University
|
|
Address:
|
4816 Horton St., Mission, KS, 66202,
|
|
Keywords:
|
Bayesian Statistics ; Adaptive Design ; Misclassification ; Clinical Trials
|
|
Abstract:
|
Among the methods that have become increasingly important in drug development are adaptive experimental designs. A primary argument for the use of adaptive designs is the efficiency one gains over implementing a traditional fixed design. We consider a simple two-arm Bayesian adaptive design utilizing adaptive allocation in which the binary outcome is subject to misclassification. A model is developed to incorporate the misclassification in the response, prior specification and issues with convergence are discussed, and we conclude with the results of a simulation study performed to assess the impact of misclassification on the efficiency and performance of the design.
|
