Robust inference on the average treatment effect using the outcome highly adaptive Lasso
From MaRDI portal
Publication:5128778
Abstract: Many estimators of the average effect of a treatment on an outcome require estimation of the propensity score, the outcome regression, or both. It is often beneficial to utilize flexible techniques such as semiparametric regression or machine learning to estimate these quantities. However, optimal estimation of these regressions does not necessarily lead to optimal estimation of the average treatment effect, particularly in settings with strong instrumental variables. A recent proposal addressed these issues via the outcome-adaptive lasso, a penalized regression technique for estimating the propensity score that seeks to minimize the impact of instrumental variables on treatment effect estimators. However, a notable limitation of this approach is that its application is restricted to parametric models. We propose a more flexible alternative that we call the outcome highly adaptive lasso. We discuss large sample theory for this estimator and propose closed form confidence intervals based on the proposed estimator. We show via simulation that our method offers benefits over several popular approaches.
Recommendations
- Model-assisted inference for treatment effects using regularized calibrated estimation with high-dimensional data
- An alternative robust estimator of average treatment effect in causal inference
- Nonparametric Inverse-Probability-Weighted Estimators Based on the Highly Adaptive Lasso
- Robust estimation of causal effects via a high-dimensional covariate balancing propensity score
- Approximate residual balancing: debiased inference of average treatment effects in high dimensions
Cited in
(20)- Valid inference for treatment effect parameters under irregular identification and many extreme propensity scores
- Heterogeneous causal effects with imperfect compliance: a Bayesian machine learning approach
- Lasso adjustments of treatment effect estimates in randomized experiments
- An alternative robust estimator of average treatment effect in causal inference
- Robust inference on average treatment effects with possibly more covariates than observations
- Heterogeneous causal inference of corporate profitability using two-scale distributional nearest neighbor estimation
- Estimation of average treatment effects with panel data: asymptotic theory and implementation
- Robust inference of conditional average treatment effects using dimension reduction
- Synthetic estimation for the complier average causal effect
- Double reinforcement learning for efficient off-policy evaluation in Markov decision processes
- A simple and general debiased machine learning theorem with finite-sample guarantees
- Reader reaction to “Outcome‐adaptive lasso: Variable selection for causal inference” by Shortreed and Ertefaie (2017)
- Estimation and inference of treatment effects with L₂-boosting in high-dimensional settings
- Neighborhood-based cross fitting approach to treatment effects with high-dimensional data
- High-dimensional Inference for Dynamic Treatment Effects
- Doubly robust adaptive LASSO for effect modifier discovery
- Non-plug-in estimators could outperform plug-in estimators: a cautionary note and a diagnosis
- Inverse-intensity weighted generalized estimating equations for longitudinal data subject to irregular observation: which variables should be included in the visit rate model?
- High-Dimensional Propensity Score and Its Machine Learning Extensions in Residual Confounding Control
- Quantile adaptive lasso: variable selection for quantile treatment effect estimation
This page was built for publication: Robust inference on the average treatment effect using the outcome highly adaptive Lasso
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5128778)
