Translator Disclaimer
February 2019 Comment: Contributions of Model Features to BART Causal Inference Performance Using ACIC 2016 Competition Data
Nicole Bohme Carnegie
Statist. Sci. 34(1): 90-93 (February 2019). DOI: 10.1214/18-STS682

Abstract

With a thorough exposition of the methods and results of the 2016 Atlantic Causal Inference Competition, Dorie et al. have set a new standard for reproducibility and comparability of evaluations of causal inference methods. In particular, the open-source R package aciccomp2016, which permits reproduction of all datasets used in the competition, will be an invaluable resource for evaluation of future methodological developments.

Building upon results from Dorie et al., we examine whether a set of potential modifications to Bayesian Additive Regression Trees (BART)—multiple chains in model fitting, using the propensity score as a covariate, targeted maximum likelihood estimation (TMLE), and computing symmetric confidence intervals—have a stronger impact on bias, RMSE, and confidence interval coverage in combination than they do alone. We find that bias in the estimate of SATT is minimal, regardless of the BART formulation. For purposes of CI coverage, however, all proposed modifications are beneficial—alone and in combination—but use of TMLE is least beneficial for coverage and results in considerably wider confidence intervals.

Citation

Download Citation

Nicole Bohme Carnegie. "Comment: Contributions of Model Features to BART Causal Inference Performance Using ACIC 2016 Competition Data." Statist. Sci. 34 (1) 90 - 93, February 2019. https://doi.org/10.1214/18-STS682

Information

Published: February 2019
First available in Project Euclid: 12 April 2019

zbMATH: 07110680
MathSciNet: MR3938969
Digital Object Identifier: 10.1214/18-STS682

Rights: Copyright © 2019 Institute of Mathematical Statistics

JOURNAL ARTICLE
4 PAGES

This article is only available to subscribers.
It is not available for individual sale.
+ SAVE TO MY LIBRARY

SHARE
Vol.34 • No. 1 • February 2019
Back to Top