BNPqte: A Bayesian Nonparametric Approach to Causal Inference on Quantiles in R

TL;DR

The paper introduces the BNPqte R package, implementing a Bayesian nonparametric approach for estimating quantile treatment effects in observational studies, offering flexible modeling and efficient computation.

Contribution

This work provides a new R package that implements a Bayesian nonparametric method for quantile causal inference, combining BART and DPM models with optimized C++ code for efficiency.

Findings

Efficient implementation of Bayesian nonparametric models in R.

Simultaneous estimation of multiple quantile treatment effects.

Improved density estimation performance over existing packages.

Abstract

In this article, we introduce the BNPqte R package which implements the Bayesian nonparametric approach of Xu, Daniels and Winterstein (2018) for estimating quantile treatment effects in observational studies. This approach provides flexible modeling of the distributions of potential outcomes, so it is capable of capturing a variety of underlying relationships among the outcomes, treatments and confounders and estimating multiple quantile treatment effects simultaneously. Specifically, this approach uses a Bayesian additive regression trees (BART) model to estimate the propensity score and a Dirichlet process mixture (DPM) of multivariate normals model to estimate the conditional distribution of the potential outcome given the estimated propensity score. The BNPqte R package provides a fast implementation for this approach by designing efficient R functions for the DPM of multivariate normals model in joint and conditional density estimation. These R functions largely improve the efficiency of the DPM model in density estimation, compared to the popular DPpackage. BART-related R functions in the BNPqte R package are inherited from the BART R package with two modifications on variable importance and split probability. To maximize computational efficiency, the actual sampling and computation for each model are carried out in C++ code. The Armadillo C++ library is also used for fast linear algebra calculations.