arbiter
JournalsAccount

Debiased Inference for Dynamic Nonlinear Panels with Multi-dimensional Heterogeneities

Xuan Leng et al.

Econometrics Journal2026https://doi.org/10.1093/ectj/utag007article
AJG 3ABDC A*
Weight
0.50

Abstract

We introduce a generic class of dynamic nonlinear heterogeneous parameter models that incorporate individual and time fixed effects in both the intercept and slope. These models are subject to the incidental parameter problem, in that the limiting distribution of the point estimator is not centered at zero, and that test statistics do not follow their standard asymptotic distributions as in the absence of the fixed effects. To address the problem, we develop an analytical bias correction procedure to construct a bias-corrected likelihood. The resulting estimator follows an asymptotic normal distribution with mean zero. Moreover, likelihood-based test statistics—including likelihood-ratio, Lagrange-multiplier, and Wald tests—follow the limiting chi-squared distribution under the null hypothesis. Simulations demonstrate the effectiveness of the proposed correction method, and an empirical application on the labor force participation of single mothers underscores its practical importance.

Open via your library →

Cite this paper

https://doi.org/https://doi.org/10.1093/ectj/utag007

Or copy a formatted citation

@article{xuan2026,
  title        = {{Debiased Inference for Dynamic Nonlinear Panels with Multi-dimensional Heterogeneities}},
  author       = {Xuan Leng et al.},
  journal      = {Econometrics Journal},
  year         = {2026},
  doi          = {https://doi.org/https://doi.org/10.1093/ectj/utag007},
}

Paste directly into BibTeX, Zotero, or your reference manager.

Flag this paper

Debiased Inference for Dynamic Nonlinear Panels with Multi-dimensional Heterogeneities

Flags are reviewed by the Arbiter methodology team within 5 business days.

Evidence weight

0.50

Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40

F · citation impact0.50 × 0.4 = 0.20
M · momentum0.50 × 0.15 = 0.07
V · venue signal0.50 × 0.05 = 0.03
R · text relevance †0.50 × 0.4 = 0.20

† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.