• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Development of consistent variable selection criteria with high-dimensional response and explanatory variables using forward-backward stepwise selection method

Research Project

Project/Area Number 20K14363
Research Category

Grant-in-Aid for Early-Career Scientists

Allocation TypeMulti-year Fund
Review Section Basic Section 12040:Applied mathematics and statistics-related
Research InstitutionHiroshima University

Principal Investigator

Oda Ryoya  広島大学, 先進理工系科学研究科(理), 助教 (10853682)

Project Period (FY) 2020-04-01 – 2024-03-31
Project Status Completed (Fiscal Year 2023)
Budget Amount *help
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2022: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2021: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2020: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Keywords多変量モデル / モデル選択 / 一致性 / 高次元 / 変数選択 / 高次元漸近理論 / 変数選択法 / 多変量解析 / 多変量線形回帰
Outline of Research at the Start

本研究の目的は, 多変量モデルにおいて, 変数の次元数が標本数を超えた場合も含んでいる高次元大標本データに対して良い性質をもつ変数選択規準を構築することである. 特に, 変数の個数が標本数を超えても実行可能な変数増減法の下で, 真の変数を選択する確率が漸近的に1となる性質である一致性をもつ変数選択規準を構築する. 目的を達成するために, まず多変量モデルの1つである多変量線形回帰モデルにおいて, 標本数は無限大だが説明変数だけでなく目的変数も標本数を超えて無限大としてよい漸近理論により一致性を評価する. 次に, 他の多変量モデルにおける変数選択規準も構築していく.

Outline of Final Research Achievements

The aim of this study is to propose a variable selection criterion with good properties for high-dimensional and large-sample data in multivariate models, including cases where the number of dimensions of the variables exceeds the sample size. In particular, we propose a criterion with consistency, which is the property that the probability of selecting the true variable is asymptotically one under a high-dimensional setting where the number of variables may exceed the sample size. In order to achieve the aim, we evaluate the consistency in multivariate models under the high-dimensional asymptotic theory, in which the sample size is infinite but the number of variables may be infinite, and propose a variable selection method with consistency.

Academic Significance and Societal Importance of the Research Achievements

近年では高次元データの使用は頻繁にされるため, そのような高次元データに対する統計分析手法の開発は重要である. 本研究により提案された変数選択手法は高次元データに対しても良い性質をもちかつ計算も高速であるため, リーズナブルな手法であると考えられる.

Report

(5 results)
  • 2023 Annual Research Report   Final Research Report ( PDF )
  • 2022 Research-status Report
  • 2021 Research-status Report
  • 2020 Research-status Report
  • Research Products

    (24 results)

All 2024 2023 2022 2021 2020 Other

All Int'l Joint Research (1 results) Journal Article (11 results) (of which Int'l Joint Research: 1 results,  Peer Reviewed: 9 results,  Open Access: 5 results) Presentation (12 results) (of which Int'l Joint Research: 5 results,  Invited: 5 results)

  • [Int'l Joint Research] SwedishUniversityofAgriculturalSciences/Linkoping University(スウェーデン)

    • Related Report
      2020 Research-status Report
  • [Journal Article] An l2,0-norm constrained matrix optimization via extended discrete first-order algorithms2023

    • Author(s)
      Oda Ryoya、Ohishi Mineaki、Suzuki Yuya、Yanagihara Hirokazu
    • Journal Title

      Hiroshima Mathematical Journal

      Volume: 53 Issue: 3 Pages: 251-267

    • DOI

      10.32917/h2021058

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] An l_2,0-norm constrained matrix optimization via extended discrete first-order algorithms2023

    • Author(s)
      Ryoya Oda, Mineaki Ohishi, Yuya Suzuki, and Hirokazu Yanagihara
    • Journal Title

      Hiroshima Mathematical Journal

      Volume: -

    • Related Report
      2022 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Kick-one-out-based variable selection method using ridge-type Cp criterion in high-dimensional multi-response linear regression models2023

    • Author(s)
      Ryoya Oda
    • Journal Title

      Intelligent Decision Technologies, Smart Innovation, Systems and Technologies

      Volume: -

    • Related Report
      2022 Research-status Report
    • Peer Reviewed
  • [Journal Article] A consistent likelihood-based variable selection method in normal multivariate linear regression2021

    • Author(s)
      Oda Ryoya、Yanagihara Hirokazu
    • Journal Title

      Smart Innovation, Systems and Technologies

      Volume: 238 Pages: 391-401

    • DOI

      10.1007/978-981-16-2765-1_33

    • ISBN
      9789811627644, 9789811627651
    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Coordinate descent algorithm for normal-likelihood-based group Lasso in multivariate linear regression2021

    • Author(s)
      Yanagihara Hirokazu、Oda Ryoya
    • Journal Title

      Smart Innovation, Systems and Technologies

      Volume: 238 Pages: 429-439

    • DOI

      10.1007/978-981-16-2765-1_36

    • ISBN
      9789811627644, 9789811627651
    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] An l_2,0-norm constrained matrix optimization via extended discrete first-order algorithms2021

    • Author(s)
      Oda Ryoya, Ohishi Mineaki, Suzuki Yuya, Yanagihara Hirokazu
    • Journal Title

      Hiroshima Statistical Research Group, Technical Report

      Volume: 21-08 Pages: 1-15

    • Related Report
      2021 Research-status Report
  • [Journal Article] On model selection consistency using a kick-one-out method for selecting response variables in high-dimensional multivariate linear regression2021

    • Author(s)
      Oda Ryoya, Yanagihara Hirokazu,Fujikoshi Yasunori
    • Journal Title

      Hiroshima Statistical Research Group, Technical Report

      Volume: 21-07 Pages: 1-15

    • Related Report
      2021 Research-status Report
  • [Journal Article] A consistent likelihood-based variable selection method in normal multivariate linear regression.2021

    • Author(s)
      Ryoya Oda, Hirokazu Yanagihara
    • Journal Title

      Smart Innovation, Systems and Technologies (KES-IDT-21)

      Volume: in press

    • Related Report
      2020 Research-status Report
    • Peer Reviewed
  • [Journal Article] Coordinate descent algorithm for normal-likelihood based group Lasso in multivariate linear regression.2021

    • Author(s)
      Hirokazu Yanagihara, Ryoya Oda
    • Journal Title

      Smart Innovation, Systems and Technologies (KES-IDT-21)

      Volume: in press

    • Related Report
      2020 Research-status Report
    • Peer Reviewed
  • [Journal Article] Consistent variable selection criteria in multivariate linear regression even when dimension exceeds sample size2020

    • Author(s)
      Oda Ryoya
    • Journal Title

      Hiroshima Mathematical Journal

      Volume: 50 Issue: 3 Pages: 339-374

    • DOI

      10.32917/hmj/1607396493

    • Related Report
      2020 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Growth Curve Model with Bilinear Random Coefficients2020

    • Author(s)
      Shinpei Imori, Dietrich von Rosen, Ryoya Oda
    • Journal Title

      Sankhya A

      Volume: in press Issue: 2 Pages: 1-32

    • DOI

      10.1007/s13171-020-00204-5

    • Related Report
      2020 Research-status Report
    • Peer Reviewed / Int'l Joint Research
  • [Presentation] Asymptotic loss efficiency of a model selection criterion in a high-dimensional GMANOVA model.2024

    • Author(s)
      Ryoya Oda
    • Organizer
      統計数理研究所 共同利用 2023 年度 重点型研究 研究集会「高次元データ解析・スパース推定法・モデル選択法の開発と融合」
    • Related Report
      2023 Annual Research Report
  • [Presentation] GMANOVAモデルとモデル選択規準の高次元漸近性質.2024

    • Author(s)
      小田凌也
    • Organizer
      岡山統計研究会 第182回研究会(学生セッション)全体レクチャー
    • Related Report
      2023 Annual Research Report
  • [Presentation] Kick-one-out-based variable selection method using ridge-type Cp criterion in high-dimensional multi-response linear regression models.2023

    • Author(s)
      Ryoya Oda
    • Organizer
      15th International KES Conference, IDT-23 (Invited Session: Recent Development of Multivariate Analysis and Model Selection)
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research / Invited
  • [Presentation] 多変量モデルにおける複合型高次元漸近理論を用いたモデル選択規準の漸近損失有効性2023

    • Author(s)
      小田凌也
    • Organizer
      多変量統計学・統計的モデル選択の新展開
    • Related Report
      2022 Research-status Report
  • [Presentation] Condition of GIC to the model minimizing KL-loss function in high-dimensional multivariate linear regression2022

    • Author(s)
      小田凌也
    • Organizer
      5th International Conference on Econometrics and Statistics (EcoSta 2022)
    • Related Report
      2022 Research-status Report
    • Int'l Joint Research / Invited
  • [Presentation] 高次元 GMANOVA モデルにおける予測のための一般化 Cp 規準の漸近性質2022

    • Author(s)
      小田凌也
    • Organizer
      2022年度統計関連学会連合大会
    • Related Report
      2022 Research-status Report
  • [Presentation] A consistent likelihood-based variable selection method in normal multivariate linear regression2021

    • Author(s)
      Oda Ryoya, Yanagihara Hirokazu
    • Organizer
      The 13th KES International Conference on Intelligent Decision Technologies
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research / Invited
  • [Presentation] A consistent variable selection method with GIC in multivariate linear regression even when dimensions are large2021

    • Author(s)
      Oda Ryoya, Yanagihara Hirokazu
    • Organizer
      4th International Conference on Econometrics and Statistics (EcoSta 2021)
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research / Invited
  • [Presentation] Asymptotically KL-loss efficiency of GIC in normal multivariate linear regression models under the high-dimensional asymptotic framework2021

    • Author(s)
      Oda Ryoya, Yanagihara Hirokazu
    • Organizer
      2021年度統計関連学会連合大会
    • Related Report
      2021 Research-status Report
  • [Presentation] 高次元多変量線形回帰における KL ロス最小化に基づくモデルの一致性2021

    • Author(s)
      Oda Ryoya, Yanagihara Hirokazu
    • Organizer
      2021年度広島大学金曜セミナー
    • Related Report
      2021 Research-status Report
  • [Presentation] Coordinate descent algorithm for normal-likelihood-based group Lasso in multivariate linear regression2021

    • Author(s)
      Yanagihara Hirokazu, Oda Ryoya
    • Organizer
      The 13th KES International Conference on Intelligent Decision Technologies
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research / Invited
  • [Presentation] 多変量線形回帰における正規尤度に基づく簡便なモデル選択法をその一致性の評価について2020

    • Author(s)
      小田凌也
    • Organizer
      広島大学金曜セミナー
    • Related Report
      2020 Research-status Report

URL: 

Published: 2020-04-28   Modified: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi