AIC for the non-concave penalized likelihood method

Yuta Umezu, Yusuke Shimizu, Hiroki Masuda, Yoshiyuki Ninomiya

研究成果: ジャーナルへの寄稿記事

1 引用 (Scopus)

抄録

Non-concave penalized maximum likelihood methods are widely used because they are more efficient than the Lasso. They include a tuning parameter which controls a penalty level, and several information criteria have been developed for selecting it. While these criteria assure the model selection consistency, they have a problem in that there are no appropriate rules for choosing one from the class of information criteria satisfying such a preferred asymptotic property. In this paper, we derive an information criterion based on the original definition of the AIC by considering minimization of the prediction error rather than model selection consistency. Concretely speaking, we derive a function of the score statistic that is asymptotically equivalent to the non-concave penalized maximum likelihood estimator and then provide an estimator of the Kullback–Leibler divergence between the true distribution and the estimated distribution based on the function, whose bias converges in mean to zero.

元の言語英語
ページ(範囲)247-274
ページ数28
ジャーナルAnnals of the Institute of Statistical Mathematics
71
発行部数2
DOI
出版物ステータス出版済み - 4 1 2019

Fingerprint

Penalized Likelihood
Information Criterion
Likelihood Methods
Penalized Maximum Likelihood
Model Selection
Score Statistic
Kullback-Leibler Divergence
Lasso
Asymptotically equivalent
Maximum Likelihood Method
Parameter Tuning
Prediction Error
Maximum Likelihood Estimator
Control Parameter
Asymptotic Properties
Penalty
Converge
Estimator
Zero

All Science Journal Classification (ASJC) codes

  • Statistics and Probability

これを引用

AIC for the non-concave penalized likelihood method. / Umezu, Yuta; Shimizu, Yusuke; Masuda, Hiroki; Ninomiya, Yoshiyuki.

:: Annals of the Institute of Statistical Mathematics, 巻 71, 番号 2, 01.04.2019, p. 247-274.

研究成果: ジャーナルへの寄稿記事

Umezu, Yuta ; Shimizu, Yusuke ; Masuda, Hiroki ; Ninomiya, Yoshiyuki. / AIC for the non-concave penalized likelihood method. :: Annals of the Institute of Statistical Mathematics. 2019 ; 巻 71, 番号 2. pp. 247-274.
@article{2f3fa205c49e4588b6bb9d19a92e8de3,
title = "AIC for the non-concave penalized likelihood method",
abstract = "Non-concave penalized maximum likelihood methods are widely used because they are more efficient than the Lasso. They include a tuning parameter which controls a penalty level, and several information criteria have been developed for selecting it. While these criteria assure the model selection consistency, they have a problem in that there are no appropriate rules for choosing one from the class of information criteria satisfying such a preferred asymptotic property. In this paper, we derive an information criterion based on the original definition of the AIC by considering minimization of the prediction error rather than model selection consistency. Concretely speaking, we derive a function of the score statistic that is asymptotically equivalent to the non-concave penalized maximum likelihood estimator and then provide an estimator of the Kullback–Leibler divergence between the true distribution and the estimated distribution based on the function, whose bias converges in mean to zero.",
author = "Yuta Umezu and Yusuke Shimizu and Hiroki Masuda and Yoshiyuki Ninomiya",
year = "2019",
month = "4",
day = "1",
doi = "10.1007/s10463-018-0649-x",
language = "English",
volume = "71",
pages = "247--274",
journal = "Annals of the Institute of Statistical Mathematics",
issn = "0020-3157",
publisher = "Springer Netherlands",
number = "2",

}

TY - JOUR

T1 - AIC for the non-concave penalized likelihood method

AU - Umezu, Yuta

AU - Shimizu, Yusuke

AU - Masuda, Hiroki

AU - Ninomiya, Yoshiyuki

PY - 2019/4/1

Y1 - 2019/4/1

N2 - Non-concave penalized maximum likelihood methods are widely used because they are more efficient than the Lasso. They include a tuning parameter which controls a penalty level, and several information criteria have been developed for selecting it. While these criteria assure the model selection consistency, they have a problem in that there are no appropriate rules for choosing one from the class of information criteria satisfying such a preferred asymptotic property. In this paper, we derive an information criterion based on the original definition of the AIC by considering minimization of the prediction error rather than model selection consistency. Concretely speaking, we derive a function of the score statistic that is asymptotically equivalent to the non-concave penalized maximum likelihood estimator and then provide an estimator of the Kullback–Leibler divergence between the true distribution and the estimated distribution based on the function, whose bias converges in mean to zero.

AB - Non-concave penalized maximum likelihood methods are widely used because they are more efficient than the Lasso. They include a tuning parameter which controls a penalty level, and several information criteria have been developed for selecting it. While these criteria assure the model selection consistency, they have a problem in that there are no appropriate rules for choosing one from the class of information criteria satisfying such a preferred asymptotic property. In this paper, we derive an information criterion based on the original definition of the AIC by considering minimization of the prediction error rather than model selection consistency. Concretely speaking, we derive a function of the score statistic that is asymptotically equivalent to the non-concave penalized maximum likelihood estimator and then provide an estimator of the Kullback–Leibler divergence between the true distribution and the estimated distribution based on the function, whose bias converges in mean to zero.

UR - http://www.scopus.com/inward/record.url?scp=85042626489&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85042626489&partnerID=8YFLogxK

U2 - 10.1007/s10463-018-0649-x

DO - 10.1007/s10463-018-0649-x

M3 - Article

AN - SCOPUS:85042626489

VL - 71

SP - 247

EP - 274

JO - Annals of the Institute of Statistical Mathematics

JF - Annals of the Institute of Statistical Mathematics

SN - 0020-3157

IS - 2

ER -