Estimation and Inference of Heterogeneous Treatment Effects using Random Forests
From MaRDI portal
Abstract: Many scientific and engineering challenges -- ranging from personalized medicine to customized marketing recommendations -- require an understanding of treatment effect heterogeneity. In this paper, we develop a non-parametric causal forest for estimating heterogeneous treatment effects that extends Breiman's widely used random forest algorithm. In the potential outcomes framework with unconfoundedness, we show that causal forests are pointwise consistent for the true treatment effect, and have an asymptotically Gaussian and centered sampling distribution. We also discuss a practical method for constructing asymptotic confidence intervals for the true treatment effect that are centered at the causal forest estimates. Our theoretical results rely on a generic Gaussian theory for a large family of random forest algorithms. To our knowledge, this is the first set of results that allows any type of random forest, including classification and regression forests, to be used for provably valid statistical inference. In experiments, we find causal forests to be substantially more powerful than classical methods based on nearest-neighbor matching, especially in the presence of irrelevant covariates.
Recommendations
- Estimating Individual Treatment Effect in Observational Data Using Random Forest Methods
- Shrinkage Bayesian Causal Forests for Heterogeneous Treatment Effects Estimation
- Model-Assisted Estimation Through Random Forests in Finite Population Sampling
- A semiparametric modeling approach using Bayesian additive regression trees with an application to evaluate heterogeneous treatment effects
- A Random Forest Approach for Bounded Outcome Variables
- Random forest estimation of conditional distribution functions and conditional quantiles
- Inference of Heterogeneous Treatment Effects using Observational Data with High-Dimensional Covariates
- scientific article; zbMATH DE number 1222135
- Random forests
Cites work
- A Class of Statistics with Asymptotically Normal Distribution
- A simple method for estimating interactions between a treatment and a large number of covariates
- Analysis of a random forests model
- Analyzing bagging
- Assessing lack of common support in causal inference using Bayesian nonparametrics: Implications for evaluating the effect of breastfeeding on children's cognitive outcomes
- Asymptotic Normality of Simple Linear Rank Statistics Under Alternatives
- Asymptotics for statistical treatment rules
- Bagging predictors
- BART: Bayesian additive regression trees
- Causal inference for statistics, social, and biomedical sciences. An introduction
- Consistency of random forests
- Consistency of random forests and other averaging classifiers
- Efficient Estimation of Average Treatment Effects Using the Estimated Propensity Score
- Estimating treatment effect heterogeneity in randomized program evaluation
- High-dimensional variable selection
- scientific article; zbMATH DE number 1894669 (Why is no real title available?)
- scientific article; zbMATH DE number 5056239 (Why is no real title available?)
- Inferring welfare maximizing treatment assignment under budget constraints
- Non-parametric tests for distributional treatment effect for randomly censored responses
- On bagging and nonlinear estimation
- On the Distribution of the Number of Admissible Points in a Vector Random Sample
- On the layered nearest neighbour estimate, the bagged nearest neighbour estimate and the random forest method in regression and classification
- On the rate of convergence of the bagged nearest neighbor estimate
- Optimal weighted nearest neighbour classifiers
- Program evaluation as a decision problem
- Quantifying uncertainty in random forests via confidence intervals and hypothesis tests
- Quantile regression forests
- Random forests
- Random Forests and Adaptive Nearest Neighbors
- Recursive partitioning for heterogeneous causal effects
- Reinforcement learning trees
- Some Comments on C P
- Standard errors for bagged and random forest estimators
- Statistical learning and selective inference
- Statistical modeling: The two cultures. (With comments and a rejoinder).
- Statistical treatment rules for heterogeneous populations.
- The central role of the propensity score in observational studies for causal effects
- The jackknife estimate of variance
- Valid post-selection inference
Cited in
(only showing first 100 items - show all)- Experimental Evaluation of Individualized Treatment Rules
- Estimating treatment effect heterogeneity in randomized program evaluation
- Individual-level social influence identification in social media: a learning-simulation coordinated method
- Learning causal effect using machine learning with application to China's typhoon
- (Machine) learning parameter regions
- Adversarial balancing-based representation learning for causal effect inference with observational data
- Doubly robust treatment effect estimation with missing attributes
- Bayesian regression tree models for causal inference: regularization, confounding, and heterogeneous effects (with discussion)
- The designed bootstrap for causal inference in big observational data
- Continuous treatment effect estimation via generative adversarial de-confounding
- Partially observable environment estimation with uplift inference for reinforcement learning based recommendation
- Uncertainty quantification for honest regression trees
- Uncertainty quantification for Bayesian CART
- An omnibus test for detection of subgroup treatment effects via data partitioning
- Beyond the mean: a flexible framework for studying causal effects using linear models
- Towards convergence rate analysis of random forests for classification
- To do or not to do? Cost-sensitive causal classification with individual treatment effect estimates
- Optimal policy trees
- Bounds on the conditional and average treatment effect with unobserved confounding factors
- Random forest estimation of conditional distribution functions and conditional quantiles
- Asymptotic properties of high-dimensional random forests
- Nonparametric feature selection by random forests and deep neural networks
- Recent advances in statistical methodologies in evaluating program for high-dimensional data
- Robust causal inference for incremental return on ad spend with randomized paired geo experiments
- Subgroup identification and variable selection for treatment decision making
- Rates of convergence for random forests via generalized U-statistics
- Robust machine learning for treatment effects in multilevel observational studies under cluster-level unmeasured confounding
- Sufficient dimension reduction for average causal effect 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
- Nonlinear predictive directions in clinical trials
- Estimation of partially conditional average treatment effect by double kernel-covariate balancing
- Estimating causal effects with optimization-based methods: a review and empirical comparison
- Modeling of time series using random forests: theoretical developments
- Minimax optimal rates for Mondrian trees and forests
- Semiparametric Bayesian causal inference
- Invariance, causality and robustness
- Rejoinder: Invariance, causality and robustness
- On IPW-based estimation of conditional average treatment effects
- Targeted smooth Bayesian causal forests: an analysis of heterogeneous treatment effects for simultaneous vs. interval medical abortion regimens over gestation
- Consistent estimation of residual variance with random forest out-of-bag errors
- Automated versus do-it-yourself methods for causal inference: lessons learned from a data analysis competition
- Non-separable models with high-dimensional data
- Constructing effective personalized policies using counterfactual inference from biased data sets with many features
- Statistical inference of heterogeneous treatment effect based on single-index model
- Smoothing and adaptation of shifted Pólya tree ensembles
- Recursive partitioning for heterogeneous causal effects
- Estimating Individual Treatment Effect in Observational Data Using Random Forest Methods
- Impact of subsampling and tree depth on random forests
- A unified framework for random forest prediction error estimation
- FLAME: a fast large-scale almost matching exactly approach to causal inference
- Estimation and inference for high dimensional generalized linear models: a splitting and smoothing approach
- Discovering heterogeneous exposure effects using randomization inference in air pollution studies
- Learning optimal distributionally robust individualized treatment rules
- Discussion of Kallus (2020) and Mo, Qi, and Liu (2020): New Objectives for Policy Learning
- Discussion of: ``More efficient policy learning via optimal retargeting and ``Learning optimal distributionally robust individualized treatment rules
- Using Machine Learning Methods to Support Causal Inference in Econometrics
- Survey-Based Forecasting: To Average or Not to Average
- scientific article; zbMATH DE number 7626801 (Why is no real title available?)
- scientific article; zbMATH DE number 7626802 (Why is no real title available?)
- Quantifying uncertainty of subsampling-based ensemble methods under a U-statistic framework
- Comparing Covariate Prioritization via Matching to Machine Learning Methods for Causal Inference Using Five Empirical Applications
- Linear Aggregation in Tree-Based Estimators
- Shrinkage Bayesian Causal Forests for Heterogeneous Treatment Effects Estimation
- A Pliable Lasso
- Boosting Random Forests to Reduce Bias; One-Step Boosted Forest and Its Variance Estimate
- Local Linear Forests
- Identifying Heterogeneous Effect Using Latent Supervised Clustering With Adaptive Fusion
- Predictive Distribution Modeling Using Transformation Forests
- Interval Censored Recursive Forests
- Consistency of survival tree and forest models: splitting bias and correction
- Discussion of the Paper “Prediction, Estimation, and Attribution” by B. Efron
- Random forests for time-dependent processes
- Randomization as regularization: a degrees of freedom explanation for random forest success
- Breaking the curse of nonregularity with subagging -- inference of the mean outcome under optimal treatment regimes
- A Sequential Significance Test for Treatment by Covariate Interactions
- Counterfactual mean embeddings
- The blessings of multiple causes
- The methods of regression applied to the stock price forecasting
- Causal interaction in factorial experiments: application to conjoint analysis
- The factor-Lasso and \(k\)-step bootstrap approach for inference in high-dimensional economic applications
- A Two-Part Framework for Estimating Individualized Treatment Rules From Semicontinuous Outcomes
- Estimation and validation of ratio-based conditional average treatment effects using observational data
- Estimation of optimal individualized treatment rules using a covariate-specific treatment effect curve with high-dimensional covariates
- Random Forest Prediction Intervals
- What are the Most Important Statistical Ideas of the Past 50 Years?
- Toward Causal Inference for Spatio-Temporal Data: Conflict and Forest Loss in Colombia
- A Semiparametric Approach to Model Effect Modification
- Manifold Oblique Random Forests: Towards Closing the Gap on Convolutional Deep Networks
- Comments on: ``A random forest guided tour
- Comments on: ``A random forest guided tour
- Towards optimal doubly robust estimation of heterogeneous causal effects
- High-Dimensional Precision Medicine From Patient-Derived Xenografts
- ROC‐guided survival trees and ensembles
- Histopathological imaging‐based cancer heterogeneity analysis via penalized fusion with model averaging
- Forward variable selection for random forest models
- Inference on heterogeneous treatment effects in high‐dimensional dynamic panels under weak dependence
- Discussion of the Paper “Prediction, Estimation, and Attribution” by B. Efron
- Dynamic Causal Effects Evaluation in A/B Testing with a Reinforcement Learning Framework
- Causal interaction trees: Finding subgroups with heterogeneous treatment effects in observational data
This page was built for publication: Estimation and Inference of Heterogeneous Treatment Effects using Random Forests
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4559704)
