|
Activity Number:
|
423
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 9, 2006 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Biopharmaceutical Section
|
| Abstract - #306209 |
|
Title:
|
A Note on Sample Size Re-estimation with Interim Binary Data for Double-blind Clinical Trials
|
|
Author(s):
|
Xiaohui Luo*+ and Peng-Liang Zhao
|
|
Companies:
|
Merck & Co., Inc. and Kyowa Pharmaceutical, Inc.
|
|
Address:
|
Clinical Biostatistics, Piscataway, NJ, 08854,
|
|
Keywords:
|
type I error ; power ; interim analysis ; dummy stratification
|
|
Abstract:
|
Shih and Zhao (1997) proposed a design with a simple stratification strategy for clinical trials with binary outcomes to re-estimate the required sample size during the trial without unblinding the interim data. A small increase in the effective type I error rate (increase about 0.01 at the significance level of 0.05) and the maintenance of an adequate effective power were shown for this design in the simulation study. Theoretical results were later derived by Govindarajulu (2005). In this talk we discuss how to choose the stratification factor in the design to control the effective type I error rate at the targeted significance level. The impact of the selected stratification factor on the effective power will also be presented.
|
