Inadmissibility of the corrected Akaike information criterion
Bernoulli · 01.05.2024 · 30 (2) · 1416-1440
DOI: 10.3150/23-bej1638 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bernoulli, erschienen am 01.05.2024. Verfasst von Takeru Matsuda. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 39 Literaturangaben.
Abstract (Originalsprache)
For the multivariate linear regression model with unknown covariance, the corrected Akaike information criterion is the minimum variance unbiased estimator of the expected Kullback–Leibler discrepancy. In this study, based on the loss estimation framework, we show its inadmissibility as an estimator of the Kullback–Leibler discrepancy itself, instead of the expected Kullback–Leibler discrepancy. We provide improved estimators of the Kullback–Leibler discrepancy that work well in reduced-rank situations and examine their performance numerically.
Zitieren
APA
Matsuda, T. (2024). Inadmissibility of the corrected Akaike information criterion. Bernoulli, 30(2), 1416-1440. https://doi.org/10.3150/23-bej1638
Vancouver
Matsuda T. Inadmissibility of the corrected Akaike information criterion. Bernoulli. 2024;30(2):1416-1440. doi:10.3150/23-bej1638
BibTeX
@article{Matsuda2024,
author = {Matsuda, Takeru},
title = {Inadmissibility of the corrected Akaike information criterion},
journal = {Bernoulli},
year = {2024},
volume = {30},
number = {2},
pages = {1416--1440},
doi = {10.3150/23-bej1638}
}
EUVIMED