Double machine learning for sample selection models

Michela Bia, Martin Huber, Lukáš Lafférs

Research output: Working paper

Abstract

This paper considers treatment evaluation when outcomes are only observed for a subpopulation due to sample selection or outcome attrition/non-response. For identification, we combine a selection-on-observables assumption for treatment assignment with either selection-on-observables or instrumental variable assumptions concerning the outcome attrition/sample selection process. To control in a data-driven way for potentially high dimensional pre-treatment covariates that motivate the selection-on-observables assumptions, we adapt the double machine learning framework to sample selection problems. That is, we make use of (a) Neyman-orthogonal and doubly robust score functions, which imply the robustness of treatment effect estimation to moderate regularization biases in the machine learning-based estimation of the outcome, treatment, or sample selection models and (b) sample splitting (or cross-fitting) to prevent overfitting bias. We demonstrate that the proposed estimators are asymptotically normal and root-n consistent under specific regularity conditions concerning the machine learners. The estimator is available in the causalweight package for the statistical software R.
Original languageEnglish
PublisherarXiv.org (Cornell University)
Number of pages36
Publication statusPublished - 9 Dec 2020

Bibliographical note

This article was submitted and deposit in arXiv : a free distribution service and an open-access archive.

Keywords

  • sample selection
  • double machine learning
  • doubly robust estimation
  • efficient score

Cite this