Saved in:
Bibliographic Details
Main Authors: Yan, Zizhong, Zhang, Zhengyu, Chen, Mingli, Li, Jingrong, Fernández-Val, Iván
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.03663
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913005015400448
author Yan, Zizhong
Zhang, Zhengyu
Chen, Mingli
Li, Jingrong
Fernández-Val, Iván
author_facet Yan, Zizhong
Zhang, Zhengyu
Chen, Mingli
Li, Jingrong
Fernández-Val, Iván
contents We develop likelihood-based bias reduction for nonlinear panel models with additive individual and time effects. In two-way panels, integrated-likelihood corrections are attractive but challenging because the required integration is high dimensional and standard Laplace approximations may fail when the parameter dimension grows with the sample size. We propose a target-centered full-exponential Laplace--cumulant expansion that exploits the sparse higher-order derivative structure implied by additive effects, delivering a tractable approximation with a negligible remainder under large-$N,T$ asymptotics. The expansion motivates robust priors that yield bias reduction for both common parameters and fixed effects. We provide implementations for binary, ordered, and multinomial response models with two-way effects. For average partial effects, we show that the remaining first-order bias has a simple variance form and can be removed by a closed-form adjustment. Monte Carlo experiments and an empirical illustration show substantial bias reduction with accurate inference.
format Preprint
id arxiv_https___arxiv_org_abs_2604_03663
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Robust Priors in Nonlinear Panel Models with Individual and Time Effects
Yan, Zizhong
Zhang, Zhengyu
Chen, Mingli
Li, Jingrong
Fernández-Val, Iván
Econometrics
Statistics Theory
We develop likelihood-based bias reduction for nonlinear panel models with additive individual and time effects. In two-way panels, integrated-likelihood corrections are attractive but challenging because the required integration is high dimensional and standard Laplace approximations may fail when the parameter dimension grows with the sample size. We propose a target-centered full-exponential Laplace--cumulant expansion that exploits the sparse higher-order derivative structure implied by additive effects, delivering a tractable approximation with a negligible remainder under large-$N,T$ asymptotics. The expansion motivates robust priors that yield bias reduction for both common parameters and fixed effects. We provide implementations for binary, ordered, and multinomial response models with two-way effects. For average partial effects, we show that the remaining first-order bias has a simple variance form and can be removed by a closed-form adjustment. Monte Carlo experiments and an empirical illustration show substantial bias reduction with accurate inference.
title Robust Priors in Nonlinear Panel Models with Individual and Time Effects
topic Econometrics
Statistics Theory
url https://arxiv.org/abs/2604.03663