Learning Objectives for Treatment Effect Estimation
Explore this paper's citation graph
Summary
This work develops a general class of two-step algorithms for heterogeneous treatment effect estimation in observational studies that has a quasi-oracle property, whereby even if the pilot estimates for marginal effects and treatment propensities are not particularly accurate, they achieve the same regret bounds as an oracle who has a-priori knowledge of these nuisance components.
- Type
- article
- Published
- 2017-12-13
- Cited by
- 67
- References
- 50
- Access
- Open access
- OpenAlex
- https://openalex.org/W2774700420
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:125273656
Keywords
Computer science, Boosting (machine learning), Oracle, Regret, A priori and a posteriori
References
- Some methods for heterogeneous treatment effect estimation in high dimensions
- Optimal Rates for Regularized Least Squares Regression
- Semiparametric Theory and Missing Data
- About the constants in Talagrand's concentration inequalities for empirical processes
- The asymptotic variance of semiparametric estimators
- Targeted Learning: Causal Inference for Observational and Experimental Data
- Rejoinder: Local Rademacher complexities and oracle inequalities in risk minimization
- Regularization in kernel learning
- Adjusting for Nonignorable Drop-Out Using Semiparametric Nonresponse Models
- Estimating Individualized Treatment Rules Using Outcome Weighted Learning
- Support vector machines
- Semiparametric Efficiency in Multivariate Regression Models with Missing Data
- CONSISTENCY OF CROSS VALIDATION FOR COMPARING REGRESSION PROCEDURES
- On Asymptotically Efficient Estimation in Semiparametric Models
- Sharper Bounds for Gaussian and Empirical Processes
- On the mathematical foundations of learning
- Bayesian Nonparametric Modeling for Causal Inference
- Comparing Experimental and Matching Methods Using a Large-Scale Voter Mobilization Experiment
- ROOT-N-CONSISTENT SEMIPARAMETRIC REGRESSION
- New concentration inequalities in product spaces
Cited by
- Efficient Policy Learning
- Metalearners for estimating heterogeneous treatment effects using machine learning
- Bayesian regression tree models for causal inference: regularization, confounding, and heterogeneous effects
- Balancing Out Regression Error: Efficient Treatment Effect Estimation without Smooth Propensities
- Augmented minimax linear estimation
- Orthogonal Random Forest for Heterogeneous Treatment Effect Estimation
- A comparison of methods for model selection when estimating individual treatment effects
- Covariate powered cross‐weighted multiple testing
- Local Linear Forests
- Transfer Learning for Estimating Causal Effects using Neural Networks
- Bounds on the conditional and average treatment effect in the presence of unobserved confounders
- Interval Estimation of Individual-Level Causal Effects Under Unobserved Confounding
- Causal Tree Estimation of Heterogeneous Household Response to Time-Of-Use Electricity Pricing Schemes
- Causaltoolbox—Estimator Stability for Heterogeneous Treatment Effects
- Machine Learning Analysis of Heterogeneity in the Effect of Student Mindset Interventions
- Minimax-inspired Semiparametric Estimation and Causal Inference
- Estimating Heterogeneous Treatment Effects Using Neural Networks With The Y-Learner
- Classifying Treatment Responders Under Causal Effect Monotonicity
- Orthogonal Statistical Learning
- Estimating Treatment Effects with Causal Forests: An Application
Related papers
- Metalearners for estimating heterogeneous treatment effects using machine learning
- Estimation and Inference of Heterogeneous Treatment Effects using Random Forests
- The central role of the propensity score in observational studies for causal effects
- Double/debiased machine learning for treatment and structural parameters
- Bayesian Nonparametric Modeling for Causal Inference
- ROOT-N-CONSISTENT SEMIPARAMETRIC REGRESSION
- Recursive partitioning for heterogeneous causal effects