A unifying approach for doubly-robust ${\ell }_1$ regularized estimation of causal contrasts

Abstract

We consider inference about a scalar parameter under a non-parametric model based on a one-step estimator computed as a plug in estimator plus the empirical mean of an estimator of the parameter's influence function. We focus on a class of parameters that have influence function which depends on two infinite dimensional nuisance functions and such that the bias of the one-step estimator of the parameter of interest is the expectation of the product of the estimation errors of the two nuisance functions. Our class includes many important treatment effect contrasts of interest in causal inference and econometrics, such as ATE, ATT, an integrated causal contrast with a continuous treatment, and the mean of an outcome missing not at random. We propose estimators of the target parameter that entertain approximately sparse regression models for the nuisance functions allowing for the number of potential confounders to be even larger than the sample size. By employing sample splitting, cross-fitting and ${\ell }_1$-regularized regression estimators of the nuisance functions based on objective functions whose directional derivatives agree with those of the parameter's influence function, we obtain estimators of the target parameter with two desirable robustness properties: (1) they are rate doubly-robust in that they are root-n consistent and asymptotically normal when both nuisance functions follow approximately sparse models, even if one function has a very non-sparse regression coefficient, so long as the other has a sufficiently sparse regression coefficient, and (2) they are model doubly-robust in that they are root-n consistent and asymptotically normal even if one of the nuisance functions does not follow an approximately sparse model so long as the other nuisance function follows an approximately sparse model with a sufficiently sparse regression coefficient.

arXiv commentfixed example 11, added example 12

References in corpus (10)

• Simultaneous analysis of Lasso and Dantzig selector
• High-dimensional regression with noisy and missing data: Provable guarantees with nonconvexity
• Robust Inference on Average Treatment Effects with Possibly More Covariates than Observations
• High-dimensional inference in misspecified linear models
• De-Biased Machine Learning of Global and Local Parameters Using Regularized Riesz Representers
• Model-assisted inference for treatment effects using regularized calibrated estimation with high-dimensional data
• Regularized calibrated estimation of propensity scores with model misspecification and high-dimensional data
• Robust Estimation of Causal Effects via High-Dimensional Covariate Balancing Propensity Score
• High Dimensional Sparse Econometric Models: An Introduction
• Honest data-adaptive inference for the average treatment effect under model misspecification using penalised bias-reduced double-robust estimation

Cited by in corpus (18)

• Double Machine Learning based Program Evaluation under Unconfoundedness
• Selective machine learning of doubly robust functionals
• Finite Sample Analysis of Minimax Offline Reinforcement Learning: Completeness, Fast Rates and First-Order Efficiency
• Estimating Treatment Effect under Additive Hazards Models with High-dimensional Covariates
• Efficient adjustment sets for population average treatment effect estimation in non-parametric causal graphical models
• The costs and benefits of uniformly valid causal inference with high-dimensional nuisance parameters
• High Dimensional M-Estimation with Missing Outcomes: A Semi-Parametric Framework
• Selective Machine Learning of the Average Treatment Effect with an Invalid Instrumental Variable
• Normalized Augmented Inverse Probability Weighting with Neural Network Predictions
• Debiased Inverse Propensity Score Weighting for Estimation of Average Treatment Effects with High-Dimensional Confounders
• Surrogate Assisted Semi-supervised Inference for High Dimensional Risk Prediction
• Regularizing Double Machine Learning in Partially Linear Endogenous Models
• Efficient adjustment sets in causal graphical models with hidden variables
• Doubly-robust evaluation of high-dimensional surrogate markers
• Treatment Effect Estimation with Observational Network Data using Machine Learning
• Efficient and Robust Semi-supervised Estimation of ATE with Partially Annotated Treatment and Response
• High-dimensional Inference for Dynamic Treatment Effects
• A Note on Debiased/Double Machine Learning Logistic Partially Linear Model