A Bayesian Nonparametric Method for Estimating Causal Treatment Effects on Zero-Inflated Outcomes
We present a Bayesian nonparametric method for estimating causal effects on continuous, 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 accrued under one treatment versus another. Cost data tend to be zero-inflated, skewed, and multi-modal. This presents a significant statistical challenge, even if the usual causal identification assumptions hold. Our approach flexibly models expected cost conditional on treatment and covariates using an infinite mixture of zero-inflated regressions. This conditional mean model is incorporated into the Bayesian standardization formula to obtain nonparametric estimates of causal effects. Moreover, the estimation procedure predicts latent cluster membership for each patient - automatically identifying patients with different cost-covariate profiles. We present a generative model, an MCMC method for sampling from the posterior and posterior predictive, and a Monte Carlo standardization procedure for computing causal effects. Our simulation studies show the resulting causal effect estimates and credible interval estimates to have low bias and close to nominal coverage, respectively. These results hold even under highly irregular data distributions. Relative to a standard infinite mixture of regressions, our method yields interval estimates with better coverage probability. We apply the method to compare inpatient costs among endometrial cancer patients receiving either chemotherapy or radiation therapy in the SEER Medicare database.
READ FULL TEXT