|
Activity Number:
|
285
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 8, 2006 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Biopharmaceutical Section
|
| Abstract - #307099 |
|
Title:
|
Sample Size Re-estimation in a Dose-Response Study
|
|
Author(s):
|
Kazuhiko Kuribayashi*+ and Mike D. Smith
|
|
Companies:
|
Pfizer Inc. and Pfizer Inc.
|
|
Address:
|
3 22 7 Yoyogi Shibuyaku, Tokyo, 151-8589, Japan
|
|
Keywords:
|
adaptive design ; treatment effect estimation ; type I error
|
|
Abstract:
|
The sample size determination is an important element in the design of a clinical trial. Re-estimation of the sample size based on an observed treatment effect during a trial can ensure an adequate power and potentially save a large amount of time and resources. The sample size re-estimation, however, prones to inflate the type I error and to exaggerate the magnitude of the treatment effect. Whereas some methodologies to control the type I error at the nominal level have been developed, issues of treatment effect estimation have not been fully resolved at the moment. In a dose-response study, it is important to estimate the treatment effect accurately. We consider a weighting approach to reduce the bias of treatment effect estimation while controlling the type I error at the nominal level in a dose-response study.
|
