Activity Number:
|
426
- SPEED: Biopharmaceutical and General Health Studies: Statistical Methods and Applications, Part 2
|
Type:
|
Contributed
|
Date/Time:
|
Tuesday, July 30, 2019 : 3:05 PM to 3:50 PM
|
Sponsor:
|
Biopharmaceutical Section
|
Abstract #307840
|
|
Title:
|
Mediation Analysis for Longitudinal Data with Applications to Clinical Trial Data
|
Author(s):
|
Yun Zhang*
|
Companies:
|
|
Keywords:
|
longitudinal data;
mediation analysis;
time-varying;
survival
|
Abstract:
|
Mediation analysis is a useful tool to understand the mechanisms for how the intervention affects outcome. Causal mediation is challenging in the context of survival outcome and time-varying mediator. Novel approaches using mediation g-formula were applied with longitudinal data in clinical studies of an antidepressant, to investigate the mediating roles of dissociative side effects on antidepressant effects. A variety of settings including time-varying mediators, time-to-event outcome are considered. We clarified the interpretation of effects in the clinical trial contexts. In addition, assumptions underlying mediation analysis and sensitivity analyses to address these have also been discussed.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2019 program
|