Saved in:
Bibliographic Details
Main Authors: Burtch, Gordon, McFowland III, Edward, Yang, Mochen, Adomavicius, Gediminas
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2303.02820
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909435433058304
author Burtch, Gordon
McFowland III, Edward
Yang, Mochen
Adomavicius, Gediminas
author_facet Burtch, Gordon
McFowland III, Edward
Yang, Mochen
Adomavicius, Gediminas
contents Despite increasing popularity in empirical studies, the integration of machine learning generated variables into regression models for statistical inference suffers from the measurement error problem, which can bias estimation and threaten the validity of inferences. In this paper, we develop a novel approach to alleviate associated estimation biases. Our proposed approach, EnsembleIV, creates valid and strong instrumental variables from weak learners in an ensemble model, and uses them to obtain consistent estimates that are robust against the measurement error problem. Our empirical evaluations, using both synthetic and real-world datasets, show that EnsembleIV can effectively reduce estimation biases across several common regression specifications, and can be combined with modern deep learning techniques when dealing with unstructured data.
format Preprint
id arxiv_https___arxiv_org_abs_2303_02820
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle EnsembleIV: Creating Instrumental Variables from Ensemble Learners for Robust Statistical Inference
Burtch, Gordon
McFowland III, Edward
Yang, Mochen
Adomavicius, Gediminas
Econometrics
Despite increasing popularity in empirical studies, the integration of machine learning generated variables into regression models for statistical inference suffers from the measurement error problem, which can bias estimation and threaten the validity of inferences. In this paper, we develop a novel approach to alleviate associated estimation biases. Our proposed approach, EnsembleIV, creates valid and strong instrumental variables from weak learners in an ensemble model, and uses them to obtain consistent estimates that are robust against the measurement error problem. Our empirical evaluations, using both synthetic and real-world datasets, show that EnsembleIV can effectively reduce estimation biases across several common regression specifications, and can be combined with modern deep learning techniques when dealing with unstructured data.
title EnsembleIV: Creating Instrumental Variables from Ensemble Learners for Robust Statistical Inference
topic Econometrics
url https://arxiv.org/abs/2303.02820