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

Theory of high-dimensional martingales and its statistical applications

Research Project

Project/Area Number 18K11203
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 60030:Statistical science-related
Research InstitutionWaseda University

Principal Investigator

Nishiyama Yoichi  早稲田大学, 国際学術院, 教授 (90270412)

Project Period (FY) 2018-04-01 – 2024-03-31
Project Status Completed (Fiscal Year 2023)
Budget Amount *help
¥3,380,000 (Direct Cost: ¥2,600,000、Indirect Cost: ¥780,000)
Fiscal Year 2022: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2021: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2020: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2019: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2018: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Keywordsマルチンゲール / 最大不等式 / 高次元統計モデル / LASSO / Dantzig selector / マルコフ連鎖 / 有向グラフ / PageRank / 順位統計量 / 統計推測 / 漸近理論 / 推定方程式 / ヒルベルト空間 / 高次元データ / 経験過程 / 高次元統計学 / 適合度検定 / 変化点検定 / 統計的推定 / 統計的仮説検定 / 確率過程
Outline of Final Research Achievements

First, I completed the proof of a "stochastic maximal inequality", which had been a long-standing challenge. The "stochastic maximalinequality" is an inequality that suppresses the maximum process of the absolute value of a finite number of local martingales by the sum of a one-dimensional predictable increasing process starting from the origin and a one-dimensional local martingale starting from the origin. As its applications, I succeeded in extending Doob's inequality and Lenglart inequality to arbitrary finite dimensions.
Next, in 2022, I published a new book, "Martingale Methods in Statistics", which aims to explain the above research results.

Academic Significance and Societal Importance of the Research Achievements

高次元統計学の昨今の潮流としては、オラクル不等式を証明したと呼称しても、実際には「確率〇〇以上で以下の不等式が成立」といった主張をされる場合が殆どである。すなわち、切り取られた部分については何の情報も提供していない。
それに対し、本研究で得られた stochastic maximal inequality は、切り取りの要素を全く含まない、完全な形の不等式である。この成果が高次元統計学の発展に与える学術的息がは大きいと考えられる。そして、それは複雑な統計モデルが用いられることの多い現代の一般社会への応用にもつながるものである。

Report

(7 results)
  • 2023 Annual Research Report   Final Research Report ( PDF )
  • 2022 Research-status Report
  • 2021 Research-status Report
  • 2020 Research-status Report
  • 2019 Research-status Report
  • 2018 Research-status Report
  • Research Products

    (10 results)

All 2023 2022 2020 2019 Other

All Int'l Joint Research (3 results) Journal Article (2 results) (of which Peer Reviewed: 2 results,  Open Access: 2 results) Presentation (4 results) (of which Int'l Joint Research: 3 results,  Invited: 3 results) Book (1 results)

  • [Int'l Joint Research] ベルガモ大学(イタリア)

    • Related Report
      2020 Research-status Report
  • [Int'l Joint Research] ベルガモ大学(イタリア)

    • Related Report
      2019 Research-status Report
  • [Int'l Joint Research] ベルガモ大学(イタリア)

    • Related Report
      2018 Research-status Report
  • [Journal Article] On rank statistics of PageRank and MarkovRank2022

    • Author(s)
      Yoichi Nishiyama
    • Journal Title

      Waseda Global Forum

      Volume: 19 Pages: 159-180

    • Related Report
      2022 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Weak convergence of marked empirical processes in a Hilbert space and its applications2020

    • Author(s)
      Tsukuda Koji、Nishiyama Yoichi
    • Journal Title

      Electronic Journal of Statistics

      Volume: 14 Issue: 2 Pages: 3914-3938

    • DOI

      10.1214/20-ejs1761

    • Related Report
      2020 Research-status Report
    • Peer Reviewed / Open Access
  • [Presentation] A stochastic maximal inequality and its applications2023

    • Author(s)
      Yoichi Nishiyama
    • Organizer
      EcoSta 2023
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research / Invited
  • [Presentation] Goodness-of-fit tests for Markovian processes based on marked empirical processes2019

    • Author(s)
      Koji Tsukuda and Yoichi Nishiyama
    • Organizer
      3rd International Conference on Econometrics and Statistics
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research / Invited
  • [Presentation] Three topics in nonparametric statistics2019

    • Author(s)
      西山陽一
    • Organizer
      Waseda International Symposium
    • Related Report
      2018 Research-status Report
    • Int'l Joint Research / Invited
  • [Presentation] マーク付き経験過程に基づくマルコフ過程の適合度検定2019

    • Author(s)
      佃康司、西山陽一
    • Organizer
      日本数学会2019年度年会
    • Related Report
      2018 Research-status Report
  • [Book] Martingale Methods in Statistics2022

    • Author(s)
      Yoichi Nishiyama
    • Total Pages
      246
    • Publisher
      CRC Press
    • ISBN
      9781466582811
    • Related Report
      2021 Research-status Report

URL: 

Published: 2018-04-23   Modified: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi