Choosing among regularized estimators in empirical economics: The risk of machine learning

Abadie, Alberto and Kasy, Maximilian ORCID: https://orcid.org/0000-0002-8679-5179 (2018) Choosing among regularized estimators in empirical economics: The risk of machine learning. Review of Economics and Statistics. (Published before print)

Full text not available from this repository.

Abstract or Table of Contents

Many settings in empirical economics involve estimation of a large number of parameters. In such settings methods that combine regularized estimation and data-driven choices of regularization parameters are useful. We provide guidance to applied researchers on (i) the choice between regularized estimators and (ii) data-driven selection of regularization parameters. We characterize the risk and relative performance of regularized estimators as a function of the data generating process, and show that data-driven choices of regularization parameters yield estimators with risk uniformly close to the risk attained under the optimal (unfeasible) choice of regularization parameters. We illustrate using examples from empirical economics.

Item Type: Article in Academic Journal
Classification Codes (e.g. JEL): C13, C14, C21
Research Units: in_Equality and Education
Status: Published before print
Date Deposited: 07 Jan 2019 13:50
Last Modified: 07 Jan 2019 13:50
URI: https://irihs.ihs.ac.at/id/eprint/4848

Actions (login required)

View Item View Item