Three Essays in Double/debiased Machine Learning and High-dimensional Econometrics

Abstract

In today’s big data world, we have witnessed rapidly increasing popularity of machine learning methods in empirical studies, such as random forests, lasso, post-lasso, elastic nets, ridge, deep neural networks, and boosted trees among others. The objective of this paper is motivated by recently increasing demand for Dou- ble/debiased Machine Learning (DML) methods in empirical research.