Estimating treatment effect heterogeneity in randomized program evaluation
From MaRDI portal
Nonparametric regression and quantile regression (62G08) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Applications of statistics to biology and medical sciences; meta analysis (62P10) Ridge regression; shrinkage estimators (Lasso) (62J07) Applications of statistics to social sciences (62P25)
Abstract: When evaluating the efficacy of social programs and medical treatments using randomized experiments, the estimated overall average causal effect alone is often of limited value and the researchers must investigate when the treatments do and do not work. Indeed, the estimation of treatment effect heterogeneity plays an essential role in (1) selecting the most effective treatment from a large number of available treatments, (2) ascertaining subpopulations for which a treatment is effective or harmful, (3) designing individualized optimal treatment regimes, (4) testing for the existence or lack of heterogeneous treatment effects, and (5) generalizing causal effect estimates obtained from an experimental sample to a target population. In this paper, we formulate the estimation of heterogeneous treatment effects as a variable selection problem. We propose a method that adapts the Support Vector Machine classifier by placing separate sparsity constraints over the pre-treatment parameters and causal heterogeneity parameters of interest. The proposed method is motivated by and applied to two well-known randomized evaluation studies in the social sciences. Our method selects the most effective voter mobilization strategies from a large number of alternative strategies, and it also identifies the characteristics of workers who greatly benefit from (or are negatively affected by) a job training program. In our simulation studies, we find that the proposed method often outperforms some commonly used alternatives.
Recommendations
- Estimation and Inference of Heterogeneous Treatment Effects using Random Forests
- Recursive partitioning for heterogeneous causal effects
- Combining estimates of conditional treatment effects
- Detecting heterogeneous treatment effects with instrumental variables and application to the Oregon Health Insurance Experiment
- Bayesian regression tree models for causal inference: regularization, confounding, and heterogeneous effects (with discussion)
Cites work
- scientific article; zbMATH DE number 3860199 (Why is no real title available?)
- scientific article; zbMATH DE number 45848 (Why is no real title available?)
- scientific article; zbMATH DE number 823069 (Why is no real title available?)
- scientific article; zbMATH DE number 845714 (Why is no real title available?)
- A robust method for estimating optimal treatment regimes
- A weakly informative default prior distribution for logistic and other regression models
- BART: Bayesian additive regression trees
- Bayesian methods for support vector machines: Evidence and predictive class probabilities
- Biometrika centenary: Theory and general methodology
- Estimating individualized treatment rules using outcome weighted learning
- Least angle regression. (With discussion)
- Model Selection and Estimation in Regression with Grouped Variables
- Multicategory Support Vector Machines
- On the ``degrees of freedom of the lasso
- Optimal Dynamic Treatment Regimes
- Performance guarantees for individualized treatment rules
- Regularization and Variable Selection Via the Elastic Net
- Reinforcement learning strategies for clinical trials in nonsmall cell lung cancer
- Soft and hard classification by reproducing kernel Hilbert space methods
- Statistical behavior and consistency of classification methods based on convex risk minimization.
- Statistical treatment rules for heterogeneous populations.
- Testing for Qualitative Interactions between Treatment Effects and Patient Subsets
- The central role of the propensity score in observational studies for causal effects
- Variable selection for support vector machines via smoothing spline ANOVA
Cited in
(70)- Comparing four methods for estimating tree-based treatment regimes
- Modelling Impact Heterogeneity
- A Generalized Quantile Tree Method for Subgroup Identification
- Regularized outcome weighted subgroup identification for differential treatment effects
- Inference on the best policies with many covariates
- Defining and estimating intervention effects for groups that will develop an auxiliary outcome
- Personalised treatment assignment maximising expected benefit with smooth hinge loss
- Estimation and Inference of Heterogeneous Treatment Effects using Random Forests
- Recursive partitioning for heterogeneous causal effects
- Estimation of causal effects using instrumental variables with nonignorable missing covariates: application to effect of type of delivery NICU on premature infants
- Nonlinear predictive directions in clinical trials
- Transfer Learning of Individualized Treatment Rules from Experimental to Real-World Data
- Permutation test for heterogeneous treatment effects with a nuisance parameter
- Asymptotic normality of a change plane estimator in fixed dimension with near-optimal rate
- High-Dimensional Precision Medicine From Patient-Derived Xenografts
- Heterogeneous indirect effects for multiple mediators using interventional effect models
- Estimating heterogeneous causal effects in observational studies using small area predictors
- A survey of personalized treatment models for pricing strategies in insurance
- Constrained optimization for stratified treatment rules in reducing hospital readmission rates of diabetic patients
- Identification of subpopulations with distinct treatment benefit rate using the Bayesian tree
- Beyond the mean: a flexible framework for studying causal effects using linear models
- A U-statistic-based test of treatment effect heterogeneity
- Some children left behind: variation in the effects of an educational intervention
- Fused comparative intervention scoring for heterogeneity of longitudinal intervention effects
- Exploration of heterogeneous treatment effects via concave fusion
- Randomization inference for treatment effect variation
- Towards optimal doubly robust estimation of heterogeneous causal effects
- Treatment recommendation and parameter estimation under single-index contrast function
- Diagnosis-group-specific transitional care program recommendations for 30-day rehospitalization reduction
- An exploratory data analysis for average treatment effect estimation based on partial balancing and simultaneous inference of regression models
- Detecting heterogeneous treatment effects with instrumental variables and application to the Oregon Health Insurance Experiment
- Bayesian regression tree models for causal inference: regularization, confounding, and heterogeneous effects (with discussion)
- Response transformation and profit decomposition for revenue uplift modeling
- Heterogeneous treatment effect-based random forest: HTERF
- A robust threshold \(t\) linear mixed model for subgroup identification using multivariate T distributions
- Quantile-optimal treatment regimes
- A Semiparametric Approach to Model Effect Modification
- Causal interaction in factorial experiments: application to conjoint analysis
- FindIt
- Learning optimal distributionally robust individualized treatment rules
- Measuring and Estimating Treatment Effect on Count Outcome in Randomized Trial and Observational Studies
- Reflections on the concept of optimality of single decision point treatment regimes
- Latent class mixture models of treatment effect heterogeneity
- Efficient Targeted Learning of Heterogeneous Treatment Effects for Multiple Subgroups
- Synthetic learner: model-free inference on treatments over time
- Combining estimates of conditional treatment effects
- Stable Discovery of Interpretable Subgroups via Calibration in Causal Studies
- Change-Plane Analysis for Subgroup Detection with a Continuous Treatment
- Investigation of age-treatment interaction in the SPACE trial using different statistical approaches
- Estimating the effect of treatments allocated by randomized waiting lists
- Multithreshold change plane model: estimation theory and applications in subgroup identification
- Experimental Evaluation of Individualized Treatment Rules
- Fairness-Oriented Learning for Optimal Individualized Treatment Rules
- Subgroup analysis using Bernoulli‐gated hierarchical mixtures of experts models
- Decomposing Treatment Effect Variation
- Comparing algorithms for characterizing treatment effect heterogeneity in randomized trials
- Longitudinal self-learning of individualized treatment rules in a nutrient supplementation trial with missing data
- Rule ensemble method with adaptive group Lasso for heterogeneous treatment effect estimation
- Robust method for optimal treatment decision making based on survival data
- A nonparametric method for value function guided subgroup identification via gradient tree boosting for censored survival data
- Propensity score weighting for causal subgroup analysis
- Modern approaches for evaluating treatment effect heterogeneity from clinical trials and observational data
- Subgroup analysis and adaptive experiments crave for debiasing
- Finding the best subgroup with differential treatment effect with multiple outcomes
- From Local to Global: External Validity in a Fertility Natural Experiment
- Multi-threshold proportional hazards model and subgroup identification
- Doubly robust adaptive LASSO for effect modifier discovery
- Assessment of heterogeneous treatment effect estimation accuracy via matching
- CAPITAL: optimal subgroup identification via constrained policy tree search
- Toward Optimal Variance Reduction in Online Controlled Experiments
This page was built for publication: Estimating treatment effect heterogeneity in randomized program evaluation
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q142565)
