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

Multivariate time series modeling with sparse regularization and its applications

Research Project

Project/Area Number 16K00067
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Research Field Statistical science
Research InstitutionThe Institute of Statistical Mathematics

Principal Investigator

Kawasaki Yoshinori  統計数理研究所, モデリング研究系, 教授 (70249910)

Project Period (FY) 2016-04-01 – 2019-03-31
Project Status Completed (Fiscal Year 2018)
Budget Amount *help
¥2,340,000 (Direct Cost: ¥1,800,000、Indirect Cost: ¥540,000)
Fiscal Year 2018: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2017: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2016: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Keywordsスパース正則化 / 円滑閾値型推定方程式 / ボラティリティ / 経験類似度 / トピックモデル / 多変量自己回帰モデル / 対数死亡率 / マスク効果 / HARモデル / モデル信頼集合 / 時系列解析 / 変数選択 / 推定方程式 / 多変量時系列
Outline of Final Research Achievements

We promoted the smooth-threshold estimation equations (STEE) to develop a prediction model with high accuracy even in high dimensional time series analysis. First, we worked with variable selection problem in volatility forecasting. We focused on empirical similarity-based models which turned out to produce better forecasting. We also compared topic score series which were extracted news text data using a dynamic topic model. Some topic score series are found to help forecasting. We also applied sparse regularization to vector autoregressive models, especially to the residual vector series from Lee-Carter model for log-mortality. Finally we proposed a variable selection method with which we can salvage true causal variables masked by other variables with strong marginal correlation.

Academic Significance and Societal Importance of the Research Achievements

IoTの推進により,学術・社会の両面でさまざまなセンサーデータが取得可能になっており,その多くは時間と共に観測される時系列データで,往々にして多変量である.従来の多変量時系列モデルは,比較的少数の変数間の相互共分散を通じてリード・ラグ関係を抽出するものであったが,ラグが深くなると高次元では推定が破綻する.本研究で試みたスパース推定との組合せは,今後の大容量の時系列解析につながる成果である.

Report

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

    (22 results)

All 2019 2018 2017 2016

All Journal Article (7 results) (of which Peer Reviewed: 5 results,  Open Access: 3 results,  Acknowledgement Compliant: 1 results) Presentation (13 results) (of which Int'l Joint Research: 10 results,  Invited: 2 results) Book (2 results)

  • [Journal Article] Forecasting Financial Market Volatility Using a Dynamic Topic Model2017

    • Author(s)
      Morimoto Takayuki、Kawasaki Yoshinori
    • Journal Title

      Asia-Pacific Financial Markets

      Volume: 24 Issue: 3 Pages: 149-167

    • DOI

      10.1007/s10690-017-9228-z

    • Related Report
      2017 Research-status Report
    • Peer Reviewed
  • [Journal Article] Detecting genetic association through shortest paths in a bidirected graph2017

    • Author(s)
      Ueki M, Kawasaki Y, Tamiya G
    • Journal Title

      Genetic Epidemiology

      Volume: 未定 Issue: 6 Pages: 481-497

    • DOI

      10.1002/gepi.22051

    • Related Report
      2017 Research-status Report
    • Peer Reviewed / Open Access / Acknowledgement Compliant
  • [Journal Article] 経験類似度に基づくボラティリティ予測2017

    • Author(s)
      森本孝之,川崎能典
    • Journal Title

      統計数理

      Volume: 65 Pages: 155-180

    • Related Report
      2017 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] 整数値自己回帰モデルの最近の発展2017

    • Author(s)
      中嶋雅彦,酒折文武,川崎能典
    • Journal Title

      統計数理

      Volume: 65 Pages: 323-339

    • NAID

      120006727375

    • Related Report
      2017 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Volatility forecasting with empirical similarity: Japanese stock market case2017

    • Author(s)
      Morimoto Takayuki, Kawasaki Yoshinori
    • Journal Title

      JSM Proceedings, Business and Economics Statistics Section

      Volume: 2017 Pages: 2483-2510

    • NAID

      120006727364

    • Related Report
      2017 Research-status Report
  • [Journal Article] VARモデルによる因果関係の推論-内閣支持率と株価を例に2017

    • Author(s)
      川崎能典
    • Journal Title

      岩波データサイエンス刊行委員会編『岩波データサイエンスVol. 6』(図書所収論文)

      Volume: 6 Pages: 68-81

    • Related Report
      2017 Research-status Report
    • Peer Reviewed
  • [Journal Article] 内閣支持率と株価の因果関係2016

    • Author(s)
      川崎能典
    • Journal Title

      応用経済時系列研究会報告集

      Volume: 33 Pages: 1-6

    • Related Report
      2016 Research-status Report
  • [Presentation] Forecasting Financial Market Volatility Using a Dynamic Topic Model2019

    • Author(s)
      Kawasaki, Y.
    • Organizer
      2019 ISI-ISM-ISSAS Joint Conference
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Value-at-Risk estimation: A novel GARCH-EVT approach dealing with bias and heteroscedasticity2019

    • Author(s)
      貝淵響, 川崎能典
    • Organizer
      第13回日本統計学会春季集会
    • Related Report
      2018 Annual Research Report
  • [Presentation] Forecasting Financial Market Volatility Using a Dynamic Topic Model2018

    • Author(s)
      Kawasaki, Y.
    • Organizer
      CEQURA Conference 2018 on Advances in Financial and Insurance Risk Management
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Comparison of EVT methods for GARCH-EVT approach applied to financial time series2018

    • Author(s)
      Kaibuchi, H., Kawasaki, Y.
    • Organizer
      11th International Conference of the ERCIM WG on Computational and Methodological Statistics
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 円滑閾値型推定方程式による与信スコアリング2018

    • Author(s)
      川崎能典
    • Organizer
      リスク解析戦略研究センター第6回金融シンポジウム
    • Related Report
      2018 Annual Research Report
  • [Presentation] Volatility forecasting with empirical similarity: Japanese stock market case2017

    • Author(s)
      Kawasaki Yoshinori, Morimoto Takayuki
    • Organizer
      CEQURA Conference 2017 on Advances in Financial and Insurance Risk Management
    • Related Report
      2017 Research-status Report
    • Int'l Joint Research
  • [Presentation] Volatility forecasting with empirical similarity: Japanese stock market case2017

    • Author(s)
      Kawasaki Yoshinori, Morimoto Takayuki
    • Organizer
      Joint Statistical Meeting 2017
    • Related Report
      2017 Research-status Report
    • Int'l Joint Research
  • [Presentation] Scale mixture of Skewed Kalman filter and its application2017

    • Author(s)
      Kawasaki Yoshinori
    • Organizer
      ISI 61st World Statistics Congress
    • Related Report
      2017 Research-status Report
    • Int'l Joint Research / Invited
  • [Presentation] 経験類似度に基づくボラティリティの推定と予測2017

    • Author(s)
      森本孝之,川崎能典
    • Organizer
      2017年度統計関連学会連合大会
    • Related Report
      2017 Research-status Report
  • [Presentation] Volatility forecasting with empirical similarity: Japanese stock market case2017

    • Author(s)
      Kawasaki Yoshinori, Morimoto Takayuki
    • Organizer
      11th International Conference on Computational and Financial Econometrics 2017
    • Related Report
      2017 Research-status Report
    • Int'l Joint Research
  • [Presentation] Volatility forecasting with empirical similarity: Japanese stock market2016

    • Author(s)
      Morimoto, T. and Kawasaki, Y
    • Organizer
      The 36th International Symposium on Forecasting
    • Place of Presentation
      Santander, Spain
    • Related Report
      2016 Research-status Report
    • Int'l Joint Research
  • [Presentation] Asymmetric modeling of price change in commodity futures2016

    • Author(s)
      Kawasaki, Y. and Aoki, Y.
    • Organizer
      First Seoul-Tokyo-Stanford Workshop on Financial Statistics and Risk Management
    • Place of Presentation
      Seoul, Korea
    • Related Report
      2016 Research-status Report
    • Int'l Joint Research / Invited
  • [Presentation] Sparse predictive modeling for bank telemarketing success using smooth-threshold estimating equations2016

    • Author(s)
      Kawasaki, Y. and Ueki, M.
    • Organizer
      Joint Statistical Meeting 2016
    • Place of Presentation
      Chicago, U.S.A.
    • Related Report
      2016 Research-status Report
    • Int'l Joint Research
  • [Book] 統計科学百科事典(「時系列回帰」pp.628-630)2018

    • Author(s)
      Miodrag Lovric、日本統計学会
    • Total Pages
      2200
    • Publisher
      丸善出版
    • ISBN
      9784621303108
    • Related Report
      2018 Annual Research Report
  • [Book] 統計科学百科事典(「ベイズ的セミパラメトリック回帰」pp.1666-1667)2018

    • Author(s)
      Miodrag Lovric、日本統計学会
    • Total Pages
      2200
    • Publisher
      丸善出版
    • ISBN
      9784621303108
    • Related Report
      2018 Annual Research Report

URL: 

Published: 2016-04-21   Modified: 2020-03-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi