|
Activity Number:
|
1
|
|
Type:
|
Invited
|
|
Date/Time:
|
Sunday, August 2, 2009 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Biopharmaceutical Section
|
| Abstract - #302788 |
|
Title:
|
On Analysis of Progression-Free-Survival
|
|
Author(s):
|
Cong Chen*+
|
|
Companies:
|
Merck Research Laboratories
|
|
Address:
|
Merck & Co., Inc., North Wales, PA, 19454,
|
|
Keywords:
|
oncology ; NPMLE ; interval-censored ; survival analysis ; sample size ; Phase III
|
|
Abstract:
|
Imbalance of assessment frequency between treatment arms causes the biggest concern in PFS analysis. Further complications include frequency of assessment, tied event times (as a result of adherence to assessment schedule), follow-up and accrual schemes. Methods robust to all sorts of data abnormalities are highly sought after. There is no widely accepted industry standard for PFS analysis. A conventional approach is to treat recorded event time as the true event times and apply the standard methods for right-censored data to the imputed data. Many bona fide interval-censored data analysis method have been proposed in the literature, but they are not routinely applied to clinical trials. In this presentation, we will show the performance of Finkelstein's nonparametric maximum likelihood estimation method in an extensive simulation study, and demonstrate its superior performance.
|
- 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 |
