Robust Inference Using Inverse Probability Weighting
Authors:
Preprint
Abstract
Inverse Probability Weighting (IPW) is widely used in program evaluation and other empirical economics applications. As Gaussian approximations perform poorly in the presence of "small denominators," trimming is routinely employed as a regularization strategy. However, ad hoc trimming of the observations renders usual inference procedures invalid for the target estimand, even in large samples. In this paper, we propose an inference procedure that is robust not only to small probability weights entering the IPW estimator, but also to a wide range of trimming threshold choices. Our inference procedure employs resampling with a novel bias correction technique. Specifically, we show that both the IPW and trimmed IPW estimators can have different (Gaussian or non-Gaussian) limiting distributions, depending on how "close to zero" the probability weights are and on the trimming threshold. Our method provides more robust inference for the target estimand by adapting to these different limiting distributions. This robustness is partly achieved by correcting a non-negligible trimming bias. We demonstrate the finite-sample accuracy of our method in a simulation study, and we illustrate its use by revisiting a dataset from the National Supported Work program.Keywords
All Related Versions
This publication has 22 references indexed in Scilit:
- Inference on finite-population treatment effects under limited overlapThe Econometrics Journal, 2019
- Asymptotic inference of causal effects with observational studies trimmed by the estimated propensity scoresBiometrika, 2018
- On the Effect of Bias Estimation on Coverage Accuracy in Nonparametric InferenceJournal of the American Statistical Association, 2018
- Approximate Residual Balancing: Debiased Inference of Average Treatment Effects in High DimensionsJournal of the Royal Statistical Society Series B: Statistical Methodology, 2018
- Robust inference on average treatment effects with possibly more covariates than observationsJournal of Econometrics, 2015
- Efficient semiparametric estimation of multi-valued treatment effects under ignorabilityJournal of Econometrics, 2010
- Inverse probability weighted estimation for general missing data problemsJournal of Econometrics, 2007
- Semiparametric instrumental variable estimation of treatment response modelsJournal of Econometrics, 2003
- Subsampling inference for the mean in the heavy-tailed caseMetrika, 1999
- Asymptotic Properties of Weighted M-estimators for variable probability samplesEconometrica, 1999