Online Program Home
My Program

Abstract Details

Activity Number: 249 - Bayesian Methods for Social and Human Data
Type: Contributed
Date/Time: Monday, July 30, 2018 : 2:00 PM to 3:50 PM
Sponsor: Section on Bayesian Statistical Science
Abstract #328693 Presentation
Title: A Bayesian Nonparametric Method for Zero-Inflated Data with Applications to Medical Costs
Author(s): Arman Oganisian* and Nandita Mitra and Jason Roy
Companies: University of Pennsylvania and University of Pennsylvania and University of Pennsylvania
Keywords: medical costs; health economics; bayesian; nonparametric; causal inference

We present a Bayesian nonparametric regression method for zero-inflated outcomes. This work is motivated by a need for estimates of causal treatment effects on medical costs; that is, estimates contrasting average total costs that would have accumulated under one treatment versus another. However, cost data tend to be heavily zero-inflated, skewed, and multi-modal. This presents a significant statistical challenge, even if the usual causal identification assumptions are satisfied. Our method flexibly models expected cost conditional on treatment and covariates. This mean model is incorporated into the g-formula to obtain nonparametric estimates of causal effects. Moreover, the estimation procedure predicts latent cluster membership for each patient - automatically identifying groups of patients who have similar cost-covariate associations. We present a generative model, an MCMC method for sampling from the posterior, and simulation results assessing regression performance under various settings. Lastly, we apply the method to costs in the SEER Medicare database.

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

Back to the full JSM 2018 program