Online Program Home
My Program

Abstract Details

Activity Number: 7 - Bayesian Nonparametrics in Causal Inference
Type: Invited
Date/Time: Sunday, July 29, 2018 : 2:00 PM to 3:50 PM
Sponsor: Section on Bayesian Statistical Science
Abstract #326590 Presentation
Title: Regularization and Aliasing in the Estimation of Treatment Effect Moderation
Author(s): Paul Richard Hahn* and Carlos Carvalho and Jared S Murray
Companies: Arizona State University and University of Texas and University of Texas at Austin
Keywords: individual treatment effects; moderation; causal inference; confounding; nonlinear regression; regularization

Nonlinear regression methods can bias estimation of treatment effects when moderating variables are codependent with the response variable in ways not due to treatment. In this case we say that the moderator is aliased with the outcome. We develop a Bayesian approach to mitigate this unintentional bias, particularly for the purpose of disentangling idiosyncratic group level effects from common covariate effects.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2018 program