Lasso penalized model selection criteria for high-dimensional multivariate linear regression analysis

Shota Katayama, Shinpei Imori

研究成果: Article査読

3 被引用数 (Scopus)

抄録

This paper proposes two model selection criteria for identifying relevant predictors in the high-dimensional multivariate linear regression analysis. The proposed criteria are based on a Lasso type penalized likelihood function to allow the high-dimensionality. Under the asymptotic framework that the dimension of multiple responses goes to infinity while the maximum size of candidate models has smaller order of the sample size, it is shown that the proposed criteria have the model selection consistency, that is, they can asymptotically pick out the true model. Simulation studies show that the proposed criteria outperform existing criteria when the dimension of multiple responses is large.

本文言語English
ページ(範囲)138-150
ページ数13
ジャーナルJournal of Multivariate Analysis
132
DOI
出版ステータスPublished - 2014 11 1
外部発表はい

ASJC Scopus subject areas

  • 統計学および確率
  • 数値解析
  • 統計学、確率および不確実性

フィンガープリント

「Lasso penalized model selection criteria for high-dimensional multivariate linear regression analysis」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル