|
Activity Number:
|
380
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 4, 2009 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #305549 |
|
Title:
|
Achieving the Benefits of an Internal Pilot with Interim Analysis While Controlling Type I Errors for Gaussian Linear Models
|
|
Author(s):
|
John A. Kairalla*+ and Keith E. Muller and Christopher S. Coffey
|
|
Companies:
|
University of Florida and University of Florida and The University of Alabama at Birmingham
|
|
Address:
|
P.O. Box 100177, Gainesville, FL, 32610-0177,
|
|
Keywords:
|
Power ; Sample Size Re-Estimation ; Internal Pilot ; Interim Analysis ; Adaptive
|
|
Abstract:
|
An internal pilot with interim analysis (IPIA) design combines interim power analysis (internal pilot) with interim data analysis (two stage group sequential) to increase study flexibility and efficiency. We provide exact small sample results for Gaussian linear models that are especially valuable for small studies in which asymptotic results do not hold. We also describe properties with sample size adjustment based on the interim error variance estimate. Two examples demonstrate that guaranteeing control of type I error rate requires some form of correction, at least with small studies. Generalizing internal pilot results leads to a bounding method that controls the type I error rate across all possible variance values with very small cost in power and expected sample size.
|
