Unified approach for the efficient inference of quantile regression models and its applications

• Project/Area Number: 15K21433
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Statistical science; Foundations of mathematics/Applied mathematics
• Research Institution: Tsuru University (2018-2019); Waseda University (2015-2017)
• Principal Investigator: Taniai Hiroyuki 都留文科大学, 教養学部, 特任准教授 (40579653)
• Project Period (FY): 2015-04-01 – 2020-03-31
• Project Status: Completed (Fiscal Year 2019)
• Budget Amount: ¥3,770,000 (Direct Cost: ¥2,900,000、Indirect Cost: ¥870,000); 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); Fiscal Year 2015: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
• Keywords: 分位数回帰 / セミパラメトリック統計 / 確率的検閲 / セミパラメトリック / 経験確率過程 / 統計数学

Outline of Final Research Achievements

In this research, we worked on the development of a method that uses a statistical model called Quantile Regression to give a better solution to the problem of optimally combining input data and converting it into an output with an acceptable stochastic behavior. It is based on efficient inferences in statistics, which allows it to be applied to various problems expressed by quantile regression models and their variants.

Academic Significance and Societal Importance of the Research Achievements

得られる入力データを最適に組み合わせることによって、許容しうる確率的挙動の出力へと変換する。これは金融分野のリスク管理から制御問題にまで求められる問題である。ここで制御・コントロールしたい対象は、出力の値ではなく、出力の確率的性質である。本研究の結果をこのような問題に適用することで「データの採り方に起因する確率的な挙動」を抑えられることが期待される。

Research Products

• [Journal Article] Circular autocorrelation of stationary circular Markov processes (2017)
  • Author(s): Abe, T., Ogata, H., Shiohama, T., and Taniai, H.
  • Journal Title: Stochastic Process and Statistical Inference Volume: 印刷中 Issue: 3 Pages: 275-290
  • DOI: 10.1007/s11203-016-9154-0
  • Peer Reviewed / Int'l Joint Research / Acknowledgement Compliant
• [Presentation] Asymptotic behavior of the alpha-risk minimizing portfolio in high-dimensional setting (2018)
  • Author(s): Hiroyuki TANIAI
  • Organizer: JSM 2018, (Joint Statistical Meeting, American Statistical Association)
  • Int'l Joint Research
• [Presentation] Minimization of a quantile-restricted problem in high-dimensional setting (2017)
  • Author(s): Hiroyuki Taniai
  • Organizer: JSM 2017, (Joint Statistical Meeting, American Statistical Association)
  • Int'l Joint Research
• [Presentation] Efficient estimation for randomly censored data with linear conditional quantiles (2016)
  • Author(s): Hiroyuki Taniai
  • Organizer: JSM 2016, (Joint Statistical Meeting, American Statistical Association)
  • Place of Presentation: Chicago
  • Year and Date: 2016-07-31
  • Int'l Joint Research
• [Presentation] A circular autocorrelation of stationary circular Markov processes (2015)
  • Author(s): Abe, T., Ogata, H., Shiohama, T. and Taniai, H.
  • Organizer: CMStatistics 2015, (8th International Conference of the ERCIM)
  • Place of Presentation: London
  • Year and Date: 2015-12-12
  • Int'l Joint Research
• [Presentation] Modeling circular Markov processes with time varying autocorrelation (2015)
  • Author(s): Abe, T., Ogata, H., Shiohama, T. and Taniai, H.
  • Organizer: CMStatistics 2015, (8th International Conference of the ERCIM)
  • Place of Presentation: London
  • Year and Date: 2015-12-12
  • Int'l Joint Research
• [Presentation] Modeling circular Markov processes with time varying autocorrelation (2015)
  • Author(s): Abe, T., Ogata, H., Shiohama, T. and Taniai, H.
  • Organizer: シンポジウム「多様な分野における統計科学の新展開」
  • Place of Presentation: 富山
  • Year and Date: 2015-10-25
• [Presentation] Efficient estimation of Quantile Regression via semiparametric mixture model (2015)
  • Author(s): Taniai, H.
  • Organizer: JSM 2015, (Joint Statistical Meeting, American Statistical Association)
  • Place of Presentation: Seattle
  • Year and Date: 2015-08-11
  • Int'l Joint Research