Bayesian regression tree models for causal inference: regularization, confounding, and heterogeneous effects (with discussion)

DOI10.1214/19-BA1195zbMath1475.62102arXiv1706.09523OpenAlexW3004404638MaRDI QIDQ2057337

Jared S. Murray, P. Richard Hahn, Carlos Marinho Carvalho

Publication date: 6 December 2021

Published in: Bayesian Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1706.09523

zbMATH Keywords

regularizationmachine learningshrinkageBayesianregression treescausal inferenceheterogeneous treatment effectspredictor-dependent priors

Mathematics Subject Classification ID

Ridge regression; shrinkage estimators (Lasso) (62J07) Applications of statistics to biology and medical sciences; meta analysis (62P10) Bayesian inference (62F15) General nonlinear regression (62J02) Causal inference from observational studies (62D20)

Related Items

Bayesian additive regression trees in spatial data analysis with sparse observations, Inference in Bayesian additive vector autoregressive tree models, Shrinkage Bayesian Causal Forests for Heterogeneous Treatment Effects Estimation, Detecting heterogeneous treatment effects with instrumental variables and application to the Oregon Health Insurance Experiment, Augmented direct learning for conditional average treatment effect estimation with double robustness, Towards optimal doubly robust estimation of heterogeneous causal effects, Heterogeneous causal effects with imperfect compliance: a Bayesian machine learning approach, BART with targeted smoothing: an analysis of patient-specific stillbirth risk, Estimating the health effects of environmental mixtures using Bayesian semiparametric regression and sparsity inducing priors, Bayesian Approaches to Shrinkage and Sparse Estimation, Estimating a causal exposure response function with a continuous error-prone exposure: a study of fine particulate matter and all-cause mortality, Causal inference: Critical developments, past and future, Classification Trees for Imbalanced Data: Surface-to-Volume Regularization, Semiparametric analysis of clustered interval‐censored survival data using soft Bayesian additive regression trees (SBART), Combining Parametric and Nonparametric Models to Estimate Treatment Effects in Observational Studies, Semiparametric Bayesian doubly robust causal estimation, Bayesian survival tree ensembles with submodel shrinkage, Causal inference under mis-specification: adjustment based on the propensity score (with discussion), Causal inference in data analysis with applications to fairness and explanations, Varying impacts of letters of recommendation on college admissions, Do forecasts of bankruptcy cause bankruptcy? A machine learning sensitivity analysis, Gibbs Priors for Bayesian Nonparametric Variable Selection with Weak Learners, Bayesian tree-based heterogeneous mediation analysis with a time-to-event outcome, Targeting customers under response-dependent costs, Targeted smooth Bayesian causal forests: an analysis of heterogeneous treatment effects for simultaneous vs. interval medical abortion regimens over gestation, Experimental Evaluation of Individualized Treatment Rules, A semiparametric modeling approach using Bayesian additive regression trees with an application to evaluate heterogeneous treatment effects, A flexible sensitivity analysis approach for unmeasured confounding with multiple treatments and a binary outcome with application to SEER-Medicare lung cancer data, Response transformation and profit decomposition for revenue uplift modeling, Bayesian additive regression trees with model trees, The designed bootstrap for causal inference in big observational data, High-dimensional confounding adjustment using continuous Spike and Slab priors, Estimating population average causal effects in the presence of non-overlap: the effect of natural gas compressor station exposure on cancer mortality, Uncertainty quantification for Bayesian CART, Automated versus do-it-yourself methods for causal inference: lessons learned from a data analysis competition, Comment: Contributions of model features to BART causal inference performance using ACIC 2016 competition data, Discovering Heterogeneous Exposure Effects Using Randomization Inference in Air Pollution Studies

Uses Software

• grf
• aciccomp2016
• BartPy

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• BART: Bayesian additive regression trees
• Doubly Robust Estimation in Missing Data and Causal Inference Models
• The prognostic analogue of the propensity score
• Estimating treatment effect heterogeneity in randomized program evaluation
• Assessing lack of common support in causal inference using Bayesian nonparametrics: Implications for evaluating the effect of breastfeeding on children's cognitive outcomes
• Generalized random forests
• The mean squared errors of the maximum likelihood and natural-conjugate Bayes regression estimators
• Regularization and confounding in linear regression for treatment effect estimation
• Disease cases and their medical costs attributable to smoking: An analysis of the national medical expenditure survey.
• Posterior concentration for Bayesian regression trees and forests
• Automated versus do-it-yourself methods for causal inference: lessons learned from a data analysis competition
• On the half-Cauchy prior for a global scale parameter
• Bayesian Treed Gaussian Process Models With an Application to Computer Modeling
• The horseshoe estimator for sparse signals
• The central role of the propensity score in observational studies for causal effects
• Estimation and Inference of Heterogeneous Treatment Effects using Random Forests
• Bayesian Regression Tree Ensembles that Adapt to Smoothness and Sparsity
• Bayesian Effect Estimation Accounting for Adjustment Uncertainty
• Estimating Exposure Effects by Modelling the Expectation of Exposure Conditional on Confounders
• Estimation and Accuracy After Model Selection
• Treatment Effects: A Bayesian Perspective
• Causal Inference for Statistics, Social, and Biomedical Sciences
• Decoupling Shrinkage and Selection in Bayesian Linear Models: A Posterior Summary Perspective
• Causal Inference With General Treatment Regimes
• Random forests
• Prior distributions for variance parameters in hierarchical models (Comment on article by Browne and Draper)