Choosing Among Regularized Estimators in Empirical Economics: The Risk of Machine Learning

• 成果类型: Article
• 署名作者: Abadie, Alberto; Kasy, Maximilian
• 署名单位: Massachusetts Institute of Technology (MIT); Harvard University
• 刊物名称: REVIEW OF ECONOMICS AND STATISTICS
• ISSN/ISSBN: 0034-6535
• DOI: 10.1162/rest_a_00812
• 发表日期: 2019-12
• 页码: 743-762
• 关键词: bayes; likelihood; selection; impacts

摘要

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 the choice between regularized estimators and 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.