Asymptotic distribution of maximum likelihood estimator in generalized linear mixed models with crossed random effects
The Annals of Statistics · 01.06.2025 · 53 (3) · 1298-1318
DOI: 10.1214/25-aos2504 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Annals of Statistics, erschienen am 01.06.2025. Verfasst von Jiming Jiang. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 15 Literaturangaben.
Abstract (Originalsprache)
Generalized linear mixed models (GLMM) with crossed random effects is infamously known to present major challenges not only computationally but also theoretically. In fact, to date only consistency of the maximum likelihood estimators (MLE) has been proved for GLMM with crosses random effects. We introduce a new technique in asymptotic analysis built on a second-order Laplace approximation (LA) of a conditional expectation, whose coefficients are carefully evaluated. The LA leads to a large system of equations involving the conditional expectations, which is asymptotically inverted to obtain explicit approximation to the conditional expectations. This powerful technique leads to a new approach to establishing asymptotic distribution of the MLE when the likelihood function is intractable. As a result, asymptotic normality of the MLE is rigorously established for GLMM with crossed random effects, bringing answer to an open problem dating back to decades ago.
Zitieren
APA
Jiang, J. (2025). Asymptotic distribution of maximum likelihood estimator in generalized linear mixed models with crossed random effects. The Annals of Statistics, 53(3), 1298-1318. https://doi.org/10.1214/25-aos2504
Vancouver
Jiang J. Asymptotic distribution of maximum likelihood estimator in generalized linear mixed models with crossed random effects. The Annals of Statistics. 2025;53(3):1298-1318. doi:10.1214/25-aos2504
BibTeX
@article{Jiang2025,
author = {Jiang, Jiming},
title = {Asymptotic distribution of maximum likelihood estimator in generalized linear mixed models with crossed random effects},
journal = {The Annals of Statistics},
year = {2025},
volume = {53},
number = {3},
pages = {1298--1318},
doi = {10.1214/25-aos2504}
}
EUVIMED