|
Activity Number:
|
115
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 3, 2009 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
WNAR
|
| Abstract - #304754 |
|
Title:
|
Sequential Monitoring Response-Adaptive Randomized Clinical Trials
|
|
Author(s):
|
Hongjian Zhu*+ and Feifang Hu
|
|
Companies:
|
University of Virginia and University of Virginia
|
|
Address:
|
212 Maury Ave, Apt 3, Charlottesville, VA, 22903,
|
|
Keywords:
|
Clinical trial ; Sequential monitoring ; Response-adaptive randomization ; Type I error
|
|
Abstract:
|
Clinical trials are complex and usually involve multiple objectives such as controlling type I error rate; increasing power; assigning more patients to better treatment; and others. In literature, both response-adaptive randomization (RAR) procedures and sequential monitoring have been proposed to achieve these objectives to some degree. In this paper, we study the possibility of combining these two sequential procedures and discuss the advantages of sequential monitoring response-adaptive randomized clinical trial. We prove that the sequential testing statistics of the combined procedure converge to a standard Brownian motion in distribution. Therefore, type I error can be well controlled theoretically by selecting the appropriate boundaries. Simulation results show that the combined procedure combines the merits of both techniques without inflating type I error.
|
