|
Activity Number:
|
233
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 3, 2009 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Biopharmaceutical Section
|
| Abstract - #303305 |
|
Title:
|
Estimation of Treatment Retention: The Peak-Trough Ratio
|
|
Author(s):
|
William J. Coar*+ and Darrin Despain and Brian L. Wiens
|
|
Companies:
|
Gilead Colorado, Inc. and Gilead Colorado, Inc. and Gilead Sciences, Inc.
|
|
Address:
|
3333 Walnut Street, Boulder, CO, 80301,
|
|
Keywords:
|
Trough-Peak Ratio ; Normal Distribution ; Cauchy Distribution ; Delta-Method ; Hinkley ; Fieller's Theorem
|
|
Abstract:
|
We consider estimation, through a ratio statistic, of the amount of treatment effect retained. The proposed peak-trough ratio is a placebo-adjusted estimator of the proportion of the peak treatment effect that remains prior to the next dosing. Under common normality assumptions, the ratio follows a distribution with undefined first and second moments. We identify distributional constraints necessary for this ratio to be meaningful. We consider techniques to provide point and interval estimates. We present a method of moments estimator for the ratio and use the delta method to approximate its variance. For interval estimation, we consider symmetric intervals, or Fieller's Theorem or Hinkley's method for asymmetric intervals. We identify the strengths and weaknesses of each method through simulations. We recommend Hinkley's percentile interval. An example is 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 2009 program |
