Online Program Home
My Program

Abstract Details

Activity Number: 599
Type: Topic Contributed
Date/Time: Wednesday, August 3, 2016 : 2:00 PM to 3:50 PM
Sponsor: Biometrics Section
Abstract #320311 View Presentation
Title: Bayesian Semiparametric Latent Mediation Model
Author(s): Chanmin Kim* and Michael Daniels and Yisheng Li
Companies: Harvard and The University of Texas at Austin and MD Anderson Cancer Center
Keywords: Semiparametric ; Bayesian Causal Inference ; Mediation ; Clusters ; Heterogeneous

In this paper, we propose a Bayesian semiparametric method to estimate heterogeneous direct and indirect effects of distinct clusters that are formed by the effect modifiers. These cluster-specific (or heterogeneous) direct and indirect effects can be estimated through a set of regression models whose individual-varying coefficients are clustered together by specifying a DP prior on the mixing distribution of the effect modifiers. Unlike other existing methods for the heterogenous effects (which require the pre-deteremed number of clusters), our model automatically detects/defines clusters. Also, to allow full flexibility of the models, we use a Bayesian semiparametric method to specify the outcome models.

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

Back to the full JSM 2016 program

Copyright © American Statistical Association