|
Activity Number:
|
215
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 13, 2002 : 12:00 PM to 1:50 PM
|
|
Sponsor:
|
Biometrics Section*
|
| Abstract - #301650 |
|
Title:
|
A Method to Assess the Proportion of Treatment Effect Explained by a Time Dependent Surrogate Endpoint
|
|
Author(s):
|
Pai-Lien Chen*+
|
|
Affiliation(s):
|
Family Health International
|
|
Address:
|
P.O. Box 13950, Research Triangle Park, North Carolina, 27709, USA
|
|
Keywords:
|
surrogate endpoint ; survival analysis ; time-dependent variable
|
|
Abstract:
|
Valid surrogate endpoints can help to control the cost and time needed to complete clinical trials to evaluate new interventions. It has been recognized that demonstrating that a surrogate endpoint captures the net effect of an intervention on the clinical efficacy endpoint is difficult, due to the complicated mechanisms of action of the intervention on the surrogate and its clinical endpoint. Li et al (2001) proposed an approach to decompose the risk of a patient before taking any intervention into three components: the risk reduction attributed to surrogate only; the risk change due to intervention but not explained by the surrogate, and the remaining risk after treatment. Based on those components, the proportion of treatment effect explained by a surrogate endpoint is estimated. Here, we extend their approach to studies with time dependent surrogate endpoints. A two-stage estimation approach is proposed and data from an actual clinical trial data is used to illustrate the proposed procedure.
|
- 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 |
