Heterogeneous causal effects with imperfect compliance: a Bayesian machine learning approach

DOI10.1214/21-AOAS1579zbMATH Open1498.62303arXiv1905.12707OpenAlexW4286484433MaRDI QIDQ2170451FDOQ2170451

Kristof De Witte, Falco J. Bargagli-Stoffi, Giorgio Gnecco

Publication date: 5 September 2022

Published in: The Annals of Applied Statistics (Search for Journal in Brave)

Abstract: This paper introduces an innovative Bayesian machine learning algorithm to draw interpretable inference on heterogeneous causal effects in the presence of imperfect compliance (e.g., under an irregular assignment mechanism). We show, through Monte Carlo simulations, that the proposed Bayesian Causal Forest with Instrumental Variable (BCF-IV) methodology outperforms other machine learning techniques tailored for causal inference in discovering and estimating the heterogeneous causal effects while controlling for the familywise error rate (or - less stringently - for the false discovery rate) at leaves' level. BCF-IV sheds a light on the heterogeneity of causal effects in instrumental variable scenarios and, in turn, provides the policy-makers with a relevant tool for targeted policies. Its empirical application evaluates the effects of additional funding on students' performances. The results indicate that BCF-IV could be used to enhance the effectiveness of school funding on students' performance.

Full work available at URL: https://arxiv.org/abs/1905.12707

zbMATH Keywords

causal inferenceheterogeneous effectsinstrumental variableschool fundinginterpretable machine learningstudents' performance

Mathematics Subject Classification ID

Bayesian inference (62F15) Applications of statistics to economics (62P20) Learning and adaptive systems in artificial intelligence (68T05) Paired and multiple comparisons; multiple testing (62J15)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Prediction with missing data via Bayesian Additive Regression Trees
• BART: Bayesian additive regression trees
• Generalized random forests
• Recursive partitioning for heterogeneous causal effects
• Identification of Causal Effects Using Instrumental Variables
• Causal Inference for Statistics, Social, and Biomedical Sciences
• The control of the false discovery rate in multiple testing under dependency.
• A stagewise rejective multiple test procedure based on a modified Bonferroni test
• A sharper Bonferroni procedure for multiple tests of significance
• On closed testing procedures with special reference to ordered analysis of variance
• The Simes Method for Multiple Hypothesis Testing With Positively Dependent Test Statistics
• Estimating Outcome Distributions for Compliers in Instrumental Variables Models
• Bayesian regression tree models for causal inference: regularization, confounding, and heterogeneous effects (with discussion)
• Bayesian inference for causal effects: The role of randomization
• Robust Nonparametric Confidence Intervals for Regression-Discontinuity Designs
• Recursive partitioning and applications
• ``Waiting for life to arrive: a history of the regression-discontinuity design in psychology, statistics and economics
• Bounds on Treatment Effects From Studies With Imperfect Compliance
• Evaluating the causal effect of university grants on student dropout: evidence from a regression discontinuity design using principal stratification
• Regression discontinuity designs: a guide to practice
• Impact evaluation in a multi-input multi-output setting: evidence on the effect of additional resources for schools
• Explanation in artificial intelligence: insights from the social sciences
• Hierarchical False Discovery Rate–Controlling Methodology
• Strong control of the familywise error rate in observational studies that discover effect modification by exploratory methods
• Discovering Heterogeneous Exposure Effects Using Randomization Inference in Air Pollution Studies
• Regularization and confounding in linear regression for treatment effect estimation
• Automated versus do-it-yourself methods for causal inference: lessons learned from a data analysis competition

Cited In (1)

• Exploiting Multivariate Outcomes in Bayesian Inference for Causal Effects with Noncompliance

This page was built for publication: Heterogeneous causal effects with imperfect compliance: a Bayesian machine learning approach

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2170451)