|
Activity Number:
|
280
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Tuesday, July 31, 2007 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
WNAR
|
| Abstract - #309694 |
|
Title:
|
Optimal Allocation in Sequential Continuous Response Experiments
|
|
Author(s):
|
Feifang Hu*+ and Hongjian Zhu
|
|
Companies:
|
University of Virginia and University of Virginia
|
|
Address:
|
Department of Statistics, Charlottesville, VA, 22904,
|
|
Keywords:
|
clinical trials ; doubly adaptive biased coin design ; power ; response-adaptive randomization
|
|
Abstract:
|
For sequential experiments with K treatments and continuous responses, we consider optimal allocations under following two formal optimization criteria: (i) maximize power of a multivariate test of homogeneity, and (ii) minimize the total expected response for a fixed power. The solutions depend on unknown parameters. We then use a response adaptive randomization procedure to target the optimal allocation. Simulation results are also reported.
|
