|
Activity Number:
|
396
- Distributional Robustness, Validity, Causality, and Generalizability
|
|
Type:
|
Invited
|
|
Date/Time:
|
Thursday, August 12, 2021 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
IMS
|
|
Abstract #316768
|
|
|
Title:
|
Increase Sample Heterogeneity to Improve the Robustness of Causal Effect Estimates
|
|
Author(s):
|
Elizabeth Tipton*
|
|
Companies:
|
Northwestern University
|
|
Keywords:
|
|
|
Abstract:
|
Historically, methods for causal inference - including both randomized trials and quasi-experiments - have focused on estimating the average causal effects of interventions. These have provided the backbone of evidence-based policy. More recently, however, analysts and policy-makers have begun pushing beyond the average, looking instead to the ability of models to predict and compare treatment effects for subgroups. For both sets of questions - regarding the average and individual predictions - however, the samples used are typically based on convenience, and can differ markedly from target populations of interest. In this talk, I discuss how these inferences and predictions can be improved by strategically recruiting the sample to maximize heterogeneity on potential moderators.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2021 program
|
