Activity Number:
|
129
|
Type:
|
Invited
|
Date/Time:
|
Monday, August 12, 2002 : 2:00 PM to 3:50 PM
|
Sponsor:
|
Biopharmaceutical Section*
|
Abstract - #300589 |
Title:
|
Adaptive Statistical Inference Following Sample Size Modification Based on Interim Review of Effect Size
|
Author(s):
|
H.M. Hung*+
|
Affiliation(s):
|
Food and Drug Administration
|
Address:
|
HFD-710, Rm 15B45, 5600 Fishers Lane, Rockville, Maryland, 20857, USA
|
Keywords:
|
group sequential trial ; non-sequential trial ; adaptive test ; type I error ; power ; estimation and confidence interval
|
Abstract:
|
In designing a comparative clinical trial, the required sample size or amount of statistical information is a function of the effect size, the value of which is unknown and at best may be estimated from historical data. Severe insufficiency in sample size as a result of overestimating the effect size can be fatal to the clinical trial. Sample size re-estimation needs to be properly considered as a part of clinical trial planning. This presentation is intended to give the motivation behind the sample size re-estimation based on an interim observed effect size and review the adaptive test strategy proposed by Cui, Hung and Wang (1999) in the group sequential trial setting where interim termination of the trial can be contemplated. This adaptive strategy is readily applicable without modification to the non-sequential trial setting, where statistical testing is performed only at the end of the trial. Methods for point and interval estimation of the treatment effect following the adaptive testing will be given. Issues of operation regarding interim adjustment of sample size will be discussed.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2002 program |