|
Activity Number:
|
247
- Causal Inference and Statistical Learning of Intervention and Policy Effects
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 11, 2021 : 10:00 AM to 11:50 AM
|
|
Sponsor:
|
Health Policy Statistics Section
|
|
Abstract #318292
|
|
|
Title:
|
A Weighted Method for Extending Inferences from a Collection of Randomized Controlled Trials
|
|
Author(s):
|
Nicole Schnitzler* and Eloise Kaizar
|
|
Companies:
|
Ohio State University and Ohio State University
|
|
Keywords:
|
Causal Inference;
Meta-analysis;
Randomized Controlled Trials;
Generalizability ;
Transportability
|
|
Abstract:
|
When multiple studies on a treatment are available, we may be interested in synthesizing the available participant data across the studies to learn what effect the treatment would have in a population of interest. Because these studies often draw from different populations, traditional meta-analytic methods may not be causally interpretable in any population outside of the population of study participants. We develop a method for extending inferences from a set of randomized clinical trials (RCTs) to a target population which accounts for the impact of participation in a particular study on treatment effects. Specifically, we propose treating the studies as clusters and introduce a consistent weighted estimator of the average treatment effect in the target population which yields causally interpretable estimates. We examine the performance of our estimator through simulations and apply our methods to a multi-center Hepatitis C RCT.
|
Authors who are presenting talks have a * after their name.
