On model selection consistency using a kick-one-out method for selecting response variables in high-dimensional multivariate linear regression

Oda Ryoya

Yanagihara Hirokazu

Fujikoshi Yasunori

Communications in Statistics - Theory and Methods

This article deals with the selection of non redundant response variables in normality-assumed multivariate linear regression, where the redundancy of the response variables is defined by conditional expectation. A sufficient condition for model selection consistency is obtained using a kick-one-out method based on the generalized information criterion under a high-dimensional asymptotic framework such that the sample size tends to infinity and the number of response variables and explanatory variables does not exceed the sample size but may tend to infinity. A consistent kick-one-out method using the obtained condition is proposed. Simulation results show that the proposed method has a high probability of selecting true, non redundant variables.

Consistency

high-dimensional criterion

multivariate calibration

variable selection

英語

Taylor & Francis

This is an Accepted Manuscript of an article published by Taylor & Francis in Communications in Statistics - Theory and Methods on 18 Jul 2024, available at: https://doi.org/10.1080/03610926.2024.2370914.

This is not the published version. Please cite only the published version.

この論文は出版社版ではありません。引用の際には出版社版をご確認、ご利用ください。

[DOI] https://doi.org/10.1080/03610926.2024.2370914 ～の異版である

日本学術振興会

Japan Society for the Promotion of Science

[Crossref Funder] https://doi.org/10.13039/501100001691

地球科学・化学・生物学的手法を組み合わせた土壌の採取地点推定に関する研究

Presumption of soil collecting point using geoscientific, chemical and biological method.

19K21672

日本学術振興会

Japan Society for the Promotion of Science

[Crossref Funder] https://doi.org/10.13039/501100001691

説明変数・目的変数が高次元でも変数増減法の下で一致性をもつ変数選択規準の開発

説明変数・目的変数が高次元でも変数増減法の下で一致性をもつ変数選択規準の開発

20K14363

日本学術振興会

Japan Society for the Promotion of Science

[Crossref Funder] https://doi.org/10.13039/501100001691

Fused-lassoによる広島・長崎の被爆に関する時空間リスク推定モデルの開発

Spatio-temporal risk models for Hiroshima and Nagasaki exposures by Fused-lasso

20H04151

日本学術振興会

Japan Society for the Promotion of Science

[Crossref Funder] https://doi.org/10.13039/501100001691

高次元データの統計分析

Statistical Analysis of High-Dimensional Data

16H03606

日本学術振興会

Japan Society for the Promotion of Science

[Crossref Funder] https://doi.org/10.13039/501100001691

高次元多変量データに対して一致性を持つ高速で簡便な変数選択法

A fast and simple consistent variable selection method for high-dimensional multivariate data

18K03415