Saved in:
Bibliographic Details
Main Authors: Wu, Peikai, Sun, Kuan, Xiao, Zhiguo
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.17910
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909053933846528
author Wu, Peikai
Sun, Kuan
Xiao, Zhiguo
author_facet Wu, Peikai
Sun, Kuan
Xiao, Zhiguo
contents We propose a double/debiased machine learning framework to estimate average derivative effects in nonparametric panel models with two-way fixed effects. It extends instrumental variable methods to panel settings, handles continuous treatments and various forms of endogeneity, and introduces a cross-fitting scheme to restore independence after eliminating time fixed effects. A penalized GMM debiasing term enables automatic debiased machine learning with endogeneity. Our estimators for contemporaneous, dynamic, and aggregated effects are consistent and asymptotically normal with a valid variance estimator. Simulations show reduced regularization bias and accurate confidence intervals. An application to ECLS-K data reveals rich dynamics in the effect of family SES on childhood BMI.
format Preprint
id arxiv_https___arxiv_org_abs_2605_17910
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Double/Debiased Machine Learning for Continuous Treatment Effects in Panel Data with Endogeneity
Wu, Peikai
Sun, Kuan
Xiao, Zhiguo
Methodology
We propose a double/debiased machine learning framework to estimate average derivative effects in nonparametric panel models with two-way fixed effects. It extends instrumental variable methods to panel settings, handles continuous treatments and various forms of endogeneity, and introduces a cross-fitting scheme to restore independence after eliminating time fixed effects. A penalized GMM debiasing term enables automatic debiased machine learning with endogeneity. Our estimators for contemporaneous, dynamic, and aggregated effects are consistent and asymptotically normal with a valid variance estimator. Simulations show reduced regularization bias and accurate confidence intervals. An application to ECLS-K data reveals rich dynamics in the effect of family SES on childhood BMI.
title Double/Debiased Machine Learning for Continuous Treatment Effects in Panel Data with Endogeneity
topic Methodology
url https://arxiv.org/abs/2605.17910