|
Activity Number:
|
27
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Sunday, August 2, 2009 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Biopharmaceutical Section
|
| Abstract - #303553 |
|
Title:
|
Flexible Sample Size Design: An Example and Additional Simulation Results
|
|
Author(s):
|
Yi He*+ and Zhenming Shun and Yijia Feng
|
|
Companies:
|
sanofi-aventis and sanofi-aventis and Penn State University
|
|
Address:
|
1608 Fox Run Drive, Plainsboro, NJ, 08536,
|
|
Keywords:
|
Adaptive Design ; Sample Size Re-estimation ; Brownian Motion ; Stopping Boundaries ; Group Sequential Design ; Conditional type I error
|
|
Abstract:
|
When sample size is modified during a trial based on interim data, the type I error can be inflated. As a result, the stopping boundaries of group sequential design need adjustment for sample size re-estimation to maintain the type I error at the pre-specified level. He et al (2009) used conditional type I error approach and derived the adjusted stopping boundaries in the group sequential design in the situation that sample size re-estimation can be performed at any interim. As supplement to the article, additional simulation results and a detailed example are provided to illustrate the method.
|
