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

Studies on screening methods for data with ultra-high dimensional covariates

Research Project

Project/Area Number 16K05268
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Research Field Foundations of mathematics/Applied mathematics
Research InstitutionHitotsubashi University

Principal Investigator

HONDA TOSHIO  一橋大学, 大学院経済学研究科, 教授 (30261754)

Research Collaborator Ing Ching-Kang  National Tsing Hua University, Institute of Statistics, Director
Wu Wei-Ying  National Dong Hua University, Department of Applied Mathematics, Assistant Professor
YABE Ryota  信州大学, 経法学部, 講師
Project Period (FY) 2016-04-01 – 2019-03-31
Project Status Completed (Fiscal Year 2018)
Budget Amount *help
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2018: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2017: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2016: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Keywords超高次元データ / 変動係数モデル / 加法モデル / Cox回帰モデル / 分位点回帰 / スプライン基底 / 高次元データ / 変数選択 / セミパラメトリックモデル / スクリーニング法
Outline of Final Research Achievements

In this research, we studied variable selection for data with ultra-high dimensional covariates. Recently the importance of such kinds of data has been increasing. There are many data sets of the kind for which linear regression models and their variants are not flexible enough to carry out data analysis. Therefore, we focused on structured nonparametric regression models such as additive models and varying coefficient models. Specifically, we dealt with simultaneous variable selection and structure identification for varying coefficient Cox models by appealing to the group Lasso. Besides, we considered quantile regression models with additive and varying coefficient structures and proposed an adaptive group Lasso method with selection consistency.

Academic Significance and Societal Importance of the Research Achievements

超高次元データの変数選択問題に関しては多くの研究があるが、変動係数モデルや加法モデルのような構造を持つノンパラメトリックモデルについては研究が遅れていた。特に超高次元の説明変数を持つ変動係数モデルおよび加法モデルから、通常の統計的推測が可能である部分線形変動係数モデルおよび部分線形加法モデルを特定化する問題は未解決であった。この問題を、スプライン基底を、定数部分、線形部分、その他と直交化し、それに応じてgroup Lassoのペナルティーを適宜分割することにより解決した。提案した手法により、通常の回帰、Cox回帰、分位点回帰で、変数選択と構造の特定化問題を扱うことができるようになった。

Report

(4 results)
  • 2018 Annual Research Report   Final Research Report ( PDF )
  • 2017 Research-status Report
  • 2016 Research-status Report
  • Research Products

    (15 results)

All 2019 2018 2017 2016 Other

All Int'l Joint Research (2 results) Journal Article (2 results) (of which Int'l Joint Research: 1 results,  Peer Reviewed: 2 results,  Open Access: 1 results) Presentation (10 results) (of which Int'l Joint Research: 7 results,  Invited: 4 results) Remarks (1 results)

  • [Int'l Joint Research] National Tsing Hua Univeristy(Taiwan)(その他の国・地域)

    • Related Report
      2018 Annual Research Report
  • [Int'l Joint Research] 国立清華大学統計学研究所(台湾)

    • Related Report
      2017 Research-status Report
  • [Journal Article] Adaptively weighted group Lasso for semiparametric quantile regression models2019

    • Author(s)
      1.Toshio Honda, Ching-Kang Ing, Wei-Ying Wu
    • Journal Title

      Bernoulli

      Volume: 印刷中

    • Related Report
      2018 Annual Research Report
    • Peer Reviewed / Int'l Joint Research
  • [Journal Article] Variable selection and structure identification for varying coefficient Cox models2017

    • Author(s)
      Toshio Honda, Ryota Yabe
    • Journal Title

      Journal of Multivariate Analysis

      Volume: 161 Pages: 103-122

    • DOI

      10.1016/j.jmva.2017.07.007

    • Related Report
      2017 Research-status Report
    • Peer Reviewed / Open Access
  • [Presentation] Adaptively weighted group Lasso for semiparametric quantile regression models2018

    • Author(s)
      Toshio Honda, Ching-Kang Ing, Wei-Ying Wu
    • Organizer
      The 5th IMS-APRM
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] The de-biased group Lasso estimation for varying coefficient models2018

    • Author(s)
      Toshio Honda
    • Organizer
      CMStatistics 2018
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Variable selection and structure identification for varying coefficient Cox models2017

    • Author(s)
      Toshio Honda, Ryota Yabe
    • Organizer
      EcoSta 2017
    • Related Report
      2017 Research-status Report
    • Int'l Joint Research / Invited
  • [Presentation] Adaptively weighted group Lasso for semiparametric quantile regression models2017

    • Author(s)
      Toshio Honda, Ching-Kang Ing, Wei-Ying Wu
    • Organizer
      European Meeting of Statisticians 2017
    • Related Report
      2017 Research-status Report
    • Int'l Joint Research
  • [Presentation] Adaptively weighted group Lasso for semiparametric quantile regression models2017

    • Author(s)
      Toshio Honda, Ching-Kang Ing, Wei-Ying Wu
    • Organizer
      CMStatistics 2017
    • Related Report
      2017 Research-status Report
    • Int'l Joint Research
  • [Presentation] Variable selection and structure identification for varying coefficient Cox models2016

    • Author(s)
      Toshio Honda, Ryota Yabe
    • Organizer
      CMStatistics 2016
    • Place of Presentation
      Seville(Spain)
    • Year and Date
      2016-12-11
    • Related Report
      2016 Research-status Report
    • Int'l Joint Research / Invited
  • [Presentation] Variable selection and structure identification for varying coefficient Cox models2016

    • Author(s)
      Toshio Honda, Ryota Yabe
    • Organizer
      科研費研究集会「応用統計学のひろがり」
    • Place of Presentation
      統計数理研究所(東京都立川市)
    • Year and Date
      2016-10-29
    • Related Report
      2016 Research-status Report
  • [Presentation] Variable selection and structure identification for varying coefficient Cox models2016

    • Author(s)
      Toshio Honda, Ryota Yabe
    • Organizer
      研究集会「大規模統計モデリングと計算統計Ⅲ」
    • Place of Presentation
      東京大学大学院数理科学研究科(東京都目黒区)
    • Year and Date
      2016-09-27
    • Related Report
      2016 Research-status Report
    • Invited
  • [Presentation] Variable selection and structure identification for varying coefficient Cox models2016

    • Author(s)
      Toshio Honda, Ryota Yabe
    • Organizer
      2016年度統計関連学会連合大会
    • Place of Presentation
      金沢大学(石川県金沢市)
    • Year and Date
      2016-09-07
    • Related Report
      2016 Research-status Report
  • [Presentation] Efficient estimation in semivarying coefficient models for longitudinal/clustered data2016

    • Author(s)
      Toshio Honda, Ming-Yen Cheng, Jialiang Li
    • Organizer
      The 4th IMS-APRM Meeting
    • Place of Presentation
      香港(中国)
    • Year and Date
      2016-06-27
    • Related Report
      2016 Research-status Report
    • Int'l Joint Research / Invited
  • [Remarks] 一橋大学研究者情報:本田敏雄

    • URL

      https://hri.ad.hit-u.ac.jp/html/449_profile_ja.html

    • Related Report
      2017 Research-status Report 2016 Research-status Report

URL: 

Published: 2016-04-21   Modified: 2022-02-22  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi