A new approach to time-series econometric analysis with point processes

• Project/Area Number: 17H02513
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Single-year Grants
• Section: 一般
• Research Field: Economic statistics
• Research Institution: Meiji University
• Principal Investigator: Kunitomo Naoto 明治大学, 政治経済学部, 特任教授 (10153313)
• Co-Investigator(Kenkyū-buntansha): 大屋 幸輔 大阪大学, 経済学研究科, 教授 (20233281) ; 佐藤 整尚 東京大学, 大学院経済学研究科(経済学部), 准教授 (60280525) ; 栗栖 大輔 東京工業大学, 工学院, 助教 (70825835)
• Project Period (FY): 2017-04-01 – 2021-03-31
• Project Status: Completed (Fiscal Year 2020)
• Budget Amount: ¥12,220,000 (Direct Cost: ¥9,400,000、Indirect Cost: ¥2,820,000); Fiscal Year 2020: ¥2,990,000 (Direct Cost: ¥2,300,000、Indirect Cost: ¥690,000); Fiscal Year 2019: ¥2,990,000 (Direct Cost: ¥2,300,000、Indirect Cost: ¥690,000); Fiscal Year 2018: ¥2,990,000 (Direct Cost: ¥2,300,000、Indirect Cost: ¥690,000); Fiscal Year 2017: ¥3,250,000 (Direct Cost: ¥2,500,000、Indirect Cost: ¥750,000)
• Keywords: 時系列分析 / 非定常時系列 / 点過程 / マクロ時系列 / 高頻度金融時系列 / Levy過程 / SIMLフィルタリング / 時系列計量分析 / 点過程アプローチ / マクロ経済時系列 / 高頻度金融データ / 時系列フィルタリング / 統計的時系列分析の理論と応用 / マクロ経済データと金融データ / 点過程(ジャンプ過程)と確率過程 / 計量経済学 / 時系列解析 / 点確率過程

Outline of Final Research Achievements

This research project has studied important issues of econometric methods based on stochastic point processes. It investigated some statistical modelling of multivariate financial time series and macro-economic time, which has been then applied to measure economic risk analysis including financial risk and insurance risk We have studied various scientific and systematic aspects of point processes and non-stationary multivariate economic time series. The project members have presented research results at various international as well as domestic academic meetings and published some books and many academic papers.
We have developed a new filtering method called the SIML (separating information maximum likelihood) method for high frequency financial data and multivariate macro- economic data. We have shown that the new method gives a new way to handle the filtering problem of macro-economic time series and also a way to find some hidden factors in high frequency financial time series

Academic Significance and Societal Importance of the Research Achievements

これまで知られていた計量分析法では社会や経済で時々起きる現象の分析は十分とは言えず、この研究プロジェクトにより点過程アプローチの重要性と限界が明らかになったことは今後のさらなる研究の基礎となることが期待される。また近年の社会・経済では事前には予想できない時々しか起きない大きな変動の理解がすすみ、対処法の設計に資すると考えられる。
なお報告書に研究プロジェクト参加者の佐藤の応用例「コロナ感染の逐次予測法」について説明した。

Research Products

• [Journal Article] Detecting factors of quadratic variation in the presence of market microstructure noise (2021)
  • Author(s): Naoto Kunitomo, Daisuke Kurisu
  • Journal Title: Japanese Journal of Statistics and Data Science Volume: － Issue: 1 Pages: 601-641
  • DOI: 10.1007/s42081-020-00104-w
  • NAID: 210000178972
  • Peer Reviewed / Open Access
• [Journal Article] A robust-filtering method for noisy non-stationary multivariate time series with econometric applications (2021)
  • Author(s): Naoto Kunitomo and Seisho Sato
  • Journal Title: Japanese Journal of Statistics and Data Science（JJSD） Volume: forthcoming Issue: 1 Pages: 373-410
  • DOI: 10.1007/s42081-020-00102-y
  • NAID: 210000167024
  • Peer Reviewed / Open Access
• [Journal Article] On the uniform convergence of deconvolution estimators from repeated measurements. (2021)
  • Author(s): Daisuke Kurisu, Taisuke OTsu
  • Journal Title: Econometric Theory Volume: － Issue: 1 Pages: 172-193
  • DOI: 10.1017/s0266466620000572
  • Peer Reviewed / Int'l Joint Research
• [Journal Article] Inference on distribution functions under measurement error (2020)
  • Author(s): Adusumilli Karun, Kurisu Daisuke, Otsu Taisuke, Whang Yoon-Jae
  • Journal Title: Journal of Econometrics Volume: 215 Issue: 1 Pages: 131-164
  • DOI: 10.1016/j.jeconom.2019.09.002
  • Peer Reviewed / Int'l Joint Research
• [Journal Article] 市場価格急変予兆の検出について (2020)
  • Author(s): 大屋幸輔
  • Journal Title: 先物・オプションレポート Volume: 32-10 Pages: 1-6
• [Journal Article] 市場価格急変予兆の検出について：応用編 (2020)
  • Author(s): 大屋幸輔
  • Journal Title: 先物・オプションレポート Volume: 32-11 Pages: 1-5
• [Journal Article] Comparing estimation methods of non-stationary errors-in-variables models (2020)
  • Author(s): Naoto Kunitomo, Naoki Awaya and Daisuke Kurisu
  • Journal Title: Japanese Journal of Statistics and Data Science Volume: ー Issue: 1 Pages: 73-101
  • DOI: 10.1007/s42081-019-00051-1
  • NAID: 210000164419
  • Peer Reviewed / Open Access / Int'l Joint Research
• [Journal Article] Bootstrap confidence bands for spectral estimation of Levy densities under high-frequency observations (2020)
  • Author(s): Kato, K. and Kurisu, D.
  • Journal Title: Stochastic Processes and their Applications Volume: ー Issue: 3 Pages: 1159-1205
  • DOI: 10.1016/j.spa.2019.04.012
  • Peer Reviewed / Int'l Joint Research
• [Journal Article] インプライド・モーメントがもたらす情報：VIXは何を伝えているのか (2019)
  • Author(s): 大屋幸輔
  • Journal Title: 『現代経済学の潮流 2019』，日本経済学会 Volume: 2019 Pages: 99-125
  • Peer Reviewed
• [Journal Article] Term Structure Models During the Global Financial Crisis: A Parsimonious Text Mining Approach (2019)
  • Author(s): Nishimura, K.G., Sato, S. & Takahashi, A
  • Journal Title: Asia-Pasific Financial Markets Volume: 297-337 Pages: 297-337
  • Peer Reviewed
• [Journal Article] On nonparametric inference for spatial regression models under domain expanding and infill asymptotics (2019)
  • Author(s): Kurisu, D
  • Journal Title: Statistics and Probability Letters Volume: 154 Pages: 108543-108543
  • DOI: 10.1016/j.spl.2019.06.019
  • Peer Reviewed
• [Journal Article] 周波数分解された分散リスク・プレミアムの予測力 (2019)
  • Author(s): 大屋幸輔
  • Journal Title: 先物・オプションレポート Volume: Vol.31 No. 1 Pages: 1-5
  • Peer Reviewed / Open Access
• [Journal Article] Simultaneous multivariate Hawkes-type point processes and their application to financial markets (2018)
  • Author(s): Kunitomo Naoto、Kurisu Daisuke、Awaya Naoki
  • Journal Title: Japanese Journal of Statistics and Data Science Volume: 1 Issue: 2 Pages: 297-332
  • DOI: 10.1007/s42081-018-0017-3
  • Peer Reviewed / Open Access
• [Journal Article] Effects of Jumps and Small Noises in High-Frequency Financial Econometrics (2017)
  • Author(s): Naoto, Kunitomo
  • Journal Title: Asia-Pacific Financial Markets Volume: 24 Issue: 1 Pages: 39-73
  • DOI: 10.1007/s10690-017-9223-4
  • Peer Reviewed / Open Access
• [Journal Article] 多次元ホークス型モデルによるマクロ金融市場の因果性分析 (2017)
  • Author(s): 国友直人・江原斐夫・栗栖大輔
  • Journal Title: 日本統計学会誌 Volume: 46-2 Pages: 137-171
  • NAID: 130006243083
  • Peer Reviewed / Open Access
• [Journal Article] ボラティリティ・スプレッド (2017)
  • Author(s): 大屋幸輔
  • Journal Title: 『先物・オプションレポート』大阪取引所 Volume: 29-12 Pages: 1-5
  • Open Access
• [Presentation] Spatially dependent wild bootstrap for high-dimensional spatial data (2021)
  • Author(s): Daisuke Kurisu
  • Organizer: University of Alberta Statistics Seminar
  • Int'l Joint Research / Invited
• [Presentation] ノイズを含む多次元非定常時系列における新しいフィ ルタリング法と応用 (2020)
  • Author(s): 国友直人
  • Organizer: 統計関連学会連合大会
• [Presentation] Wild bootstrap for spatio-temporal data (2020)
  • Author(s): Daisuke Kurisu
  • Organizer: CMStatistics 2020
  • Int'l Joint Research / Invited
• [Presentation] Estimation of smoothly time varying coefficient partial adjustment model (2019)
  • Author(s): Kosuke Oya
  • Organizer: The 3rd International Conference on Econometrics and Statistics (EcoSta2019)
  • Int'l Joint Research / Invited
• [Presentation] Term Structure Models During the Global Financial Crisis: A Parsimonious Text Mining Approach (2019)
  • Author(s): Seisho Sato
  • Organizer: ICMMA
  • Int'l Joint Research / Invited
• [Presentation] インプライド・モーメントがもたらす情報：VIXは何を伝えているのか (2018)
  • Author(s): 大屋幸輔
  • Organizer: 日本経済学会2018年度秋季大会
• [Presentation] Detecting Numbers Factors in Non-Stationary Errors-in-Variables Models (2018)
  • Author(s): 国友直人
  • Organizer: 科学研究プロジェクト「新しい時系列計量分析の理論と応用」
  • Int'l Joint Research
• [Presentation] 不等間隔観測の下でのノンパラメトリック空間回帰モデルに対する統計的推測 (2018)
  • Author(s): 栗栖大輔
  • Organizer: 科学研究プロジェクト「新しい時系列計量分析の理論と応用」
  • Int'l Joint Research
• [Presentation] Local SIML Estimation of Some Brownian Functionals (2018)
  • Author(s): 佐藤整尚・国友直人
  • Organizer: 科学研究プロジェクト「新しい時系列計量分析の理論と応用」
  • Int'l Joint Research
• [Presentation] High-frequency Financial Data and G-Causality Analysis (2017)
  • Author(s): Kosuke Oya
  • Organizer: The 1st International Conference on Econometrics and Statistics
  • Int'l Joint Research / Invited
• [Presentation] GDPの見方について (2017)
  • Author(s): 佐藤整尚
  • Organizer: 研究集会「新しい時系列計量分析の理論と応用」
  • Invited
• [Book] 極値現象の統計分析 ―裾の重い分布のモデリング― (2021)
  • Author(s): 国友直人 ・栗栖大輔
  • Total Pages: 413
  • Publisher: 朝倉書店
  • ISBN: 9784254122565
• [Book] データ分析のための統計学入門 (2021)
  • Author(s): 国友直人, 小暮厚之, 吉田靖
  • Total Pages: 426
  • Publisher: 日本統計協会
  • ISBN: 9784822341053
• [Book] 統計と日本社会：データサイエンス時代の展開 (2019)
  • Author(s): 国友直人、山本拓
  • Total Pages: 293
  • Publisher: 東京大学出版会
  • ISBN: 4130434012
• [Book] Separating Information Maximum Likelihood Method for High-Frequency Financial Data (2018)
  • Author(s): Naoto Kunitomo, Seisho Sato Daisuke Kurisu
  • Total Pages: 114
  • Publisher: Springer
  • ISBN: 9784431559283
• [Book] Characterizing Interdependencies of Multiple Time Series: Theory and Applications (2017)
  • Author(s): Yuzo Hosoya, Kosuke Oya, Taro Takimoto, Ryo Kinoshita
  • Total Pages: 133
  • Publisher: Springer
  • ISBN: 9789811064357
• [Funded Workshop] データサイエンス・松本キャンプ (2018)