Development of statistical modeling with regularization for large scale data

• Project/Area Number: 25730017
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Statistical science
• Research Institution: Kyushu University
• Principal Investigator: Matsui Hidetoshi 九州大学, 数理(科)学研究科(研究院), 助教 (90633305)
• Project Period (FY): 2013-04-01 – 2016-03-31
• Project Status: Completed (Fiscal Year 2015)
• Budget Amount: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000); Fiscal Year 2015: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000); Fiscal Year 2014: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000); Fiscal Year 2013: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
• Keywords: 関数データ解析 / スパース正則化 / モデル選択 / 経時測定データ解析 / 繰り返し測定データ解析 / 統計数学

Outline of Final Research Achievements

I have developed some statistical modeling strategies for repeated measurement or longitudinal data in order to extract important information from data. In this work I focused on two topics; functional data analysis and sparse regularization. The basic idea behind functional data analysis is to express longitudinal data in the form of a function and then draw information from a set of functional data. I applied sparse regularization techniques to several statistical models for functional data in order to estimate model and select functional variables simultaneously. I also derived algorithms for estimating parameters and model selection criteria for evaluating the estimated models. The proposed methods were applied to the analyses of real data sets and then examined the effectiveness of the methods.

Research Products

• [Journal Article] A Trans-omics Mathematical Analysis Reveals Novel Functions of the Ornithine Metabolic Pathway in Cancer Stem Cells. (2016)
  • Author(s): Koseki, J., Matsui, H., Konno, M., Nishida, N., Kawamoto, K., Kano, Y., Mori, M., Doki, Y., Ishii, H.
  • Journal Title: Sci Rep. Volume: 6 Issue: 1 Pages: 20726-20726
  • DOI: 10.1038/srep20726
  • Peer Reviewed / Open Access
• [Journal Article] Gene set differential analysis of time course expression profiles via sparse estimation in functional logistic model with application to time-dependent biomarker detection (2016)
  • Author(s): Kayano M, Matsui H, Yamaguchi R, Imoto S, Miyano S
  • Journal Title: Biostatistics Volume: 17 Issue: 2 Pages: 235-248
  • DOI: 10.1093/biostatistics/kxv037
  • Peer Reviewed
• [Journal Article] 非線形混合効果モデルに基づく関数データクラスタリング (2016)
  • Author(s): 松井秀俊，三角俊裕，横溝孝明，小西貞則
  • Journal Title: 応用統計学 Volume: 45 Pages: 0-0
  • NAID: 130005171068
  • Peer Reviewed / Acknowledgement Compliant
• [Journal Article] Sparse regularization for bi-level variable selection (2015)
  • Author(s): Matsui, H.
  • Journal Title: Journal of the Japanese Society of Computational Statistics Volume: 28 Pages: 83-103
  • NAID: 130005434007
  • Peer Reviewed / Acknowledgement Compliant
• [Journal Article] Selection of decision boundaries for logistic regression (2015)
  • Author(s): Matsui, H.
  • Journal Title: Bulletin of Informatics and Cybernetics Volume: 47 Pages: 83-95
  • NAID: 120006401435
  • Peer Reviewed / Acknowledgement Compliant
• [Journal Article] Mathematical analysis predicts imbalanced IDH1/2 expression associates with 2-HG-inactivating β-oxygenation pathway in colorectal cancer (2015)
  • Author(s): Koseki, J., Colvin, H., Fukusumi, T., Nishida, N., Konno, M., Kawamoto, K., Tsunekuni, K., Matsui, H., Doki, Y., Mori, M. and Ishii, H.
  • Journal Title: International Journal of Oncology Volume: 46 Issue: 3 Pages: 1181-1191
  • DOI: 10.3892/ijo.2015.2833
  • Peer Reviewed
• [Journal Article] Variable selection for varying coefficient models with the sparse regularization (2015)
  • Author(s): Matsui, H. and Misumi, T.
  • Journal Title: Computational Statistics Volume: 30 Issue: 1 Pages: 43-55
  • DOI: 10.1007/s00180-014-0520-3
  • NAID: 120005526397
  • Peer Reviewed / Acknowledgement Compliant
• [Journal Article] Pyruvate kinase M2, but not M1, allele maintains immature metabolic states of murine embryonic stem cells (2015)
  • Author(s): Konno, M., Ishii, H., Koseki, J., Tanuma, N., Nishida, N., Kawamoto, K., Nishimura, T., Nakata, A., Matsui, H., Noguchi, K., Ozaki, M., Noguchi, Y., Shima, H., Gotoh N., Nagano, H., Doki, Y. and Mori, M.
  • Journal Title: Regenerative Therapy Volume: 1 Pages: 63-71
  • DOI: 10.1016/j.reth.2015.01.001
  • Peer Reviewed / Open Access
• [Journal Article] Model selection criteria for the varying-coefficient modeling via regularized basis expansions (2014)
  • Author(s): Matsui, H., Misumi, T. and Kawano, S.
  • Journal Title: Journal of Statistical Computation and Simulation Volume: 84 Issue: 10 Pages: 2156-2165
  • DOI: 10.1080/00949655.2013.785548
  • Peer Reviewed
• [Journal Article] Variable and boundary selection for functional data via multiclass logistic regression modeling (2014)
  • Author(s): Matsui, H.
  • Journal Title: Computational Statistics and Data Analysis Volume: 78 Pages: 176-185
  • DOI: 10.1016/j.csda.2014.04.015
  • NAID: 120005527740
  • Peer Reviewed
• [Presentation] Sparse regularization for multiclass functional logistic regression (2016)
  • Author(s): Matsui, H.
  • Organizer: The 4th Institute of Mathematical Statistics Asia Pacific Rim Meeting
  • Place of Presentation: University of Hong Kong
  • Year and Date: 2016-06-27
  • Int'l Joint Research
• [Presentation] Sparse regularization for historical functional linear model (2016)
  • Author(s): 松井秀俊
  • Organizer: 計算機統計学会第３０回大会
  • Place of Presentation: ハートピア京都
  • Year and Date: 2016-05-19
• [Presentation] 経時測定データに対する数理統計的アプローチと医療における遺伝子データ解析 (2016)
  • Author(s): 松井秀俊，茅野光範，山口類，井元清哉，宮野悟
  • Organizer: シンポジウム「生命データ科学による新たな社会的価値の創造～医療，農業，環境分野における役割と作物設計への応用～」
  • Place of Presentation: 理化学研究所
  • Year and Date: 2016-02-22
• [Presentation] スパース正則化に基づく関数データ判別による遺伝子データ解析 (2016)
  • Author(s): 松井秀俊
  • Organizer: Statistical Bioinformatics Seminar
  • Place of Presentation: 京都大学
  • Year and Date: 2016-01-29
• [Presentation] Selection of variable and classification boundary for functional data by logistic regression (2015)
  • Author(s): Matsui, H.
  • Organizer: 9th Conference of the Asian Regional Section of the IASC
  • Place of Presentation: National University of Singapore, Singapore
  • Year and Date: 2015-12-17
  • Int'l Joint Research
• [Presentation] Classification of functional data using bi-level selection (2015)
  • Author(s): Matsui, H.
  • Organizer: 8th International Conference of the ERCIM WG on Computational and Methodological Statistics
  • Place of Presentation: University of London
  • Year and Date: 2015-12-12
  • Int'l Joint Research / Invited
• [Presentation] スパース正則化を用いた関数データの判別および変数・決定境界の選択 (2015)
  • Author(s): 松井秀俊
  • Organizer: データ科学特別セミナー
  • Place of Presentation: 大阪大学
  • Year and Date: 2015-11-20
• [Presentation] Selection of functional variables and classification boundaries via the sparse group lasso (2015)
  • Author(s): Matsui, H.
  • Organizer: International Workshop for JSCS 30th Anniversary
  • Place of Presentation: Okinawa Institute of Science and Technology Graduate University
  • Year and Date: 2015-10-30
  • Int'l Joint Research / Invited
• [Presentation] スパース正則化に基づく経時測定データの判別と遺伝子データ解析への応用 (2015)
  • Author(s): 松井秀俊
  • Organizer: 科研費シンポジウム「生命科学データ解析の方法論と健康科学への応用」
  • Place of Presentation: 東京大学医科学研究所
  • Year and Date: 2015-10-16
• [Presentation] Bi-level selectionを用いた関数ロジスティック回帰モデルの推定 (2015)
  • Author(s): 松井秀俊
  • Organizer: 2015年度統計関連学会連合大会
  • Place of Presentation: 岡山大学
  • Year and Date: 2015-09-07
• [Presentation] Selection of variable and classification boundary by functional logistic regression (2014)
  • Author(s): Matsui, H.
  • Organizer: 7th International Conference of the ERCIM WG on Computational and Methodological Statistics
  • Place of Presentation: University of Pisa
  • Year and Date: 2014-12-06 – 2014-12-09
  • Invited
• [Presentation] Regression models for functional data and variable selection via the sparse regularization (2014)
  • Author(s): 松井秀俊
  • Organizer: Workshop on Statistical Methods for Large Complex Data
  • Place of Presentation: 筑波大学
  • Year and Date: 2014-11-10 – 2014-11-12
• [Presentation] スパース正則化に基づく関数多変量回帰モデルの推定 (2014)
  • Author(s): 松井秀俊
  • Organizer: 2014年度統計関連学会連合大会
  • Place of Presentation: 東京大学
  • Year and Date: 2014-09-14 – 2014-09-17
• [Presentation] Variable selection in multivariate linear models for functional data (2014)
  • Author(s): Matsui, H.
  • Organizer: 21st Conference on Computational Statistics
  • Place of Presentation: The International Conference Center Geneva
  • Year and Date: 2014-08-19 – 2014-08-22
• [Presentation] 関数データに基づく多変量回帰モデルとスパース正則化による推定 (2014)
  • Author(s): 松井秀俊
  • Organizer: 統計サマーセミナー2014
  • Place of Presentation: 森秋旅館
  • Year and Date: 2014-08-01 – 2014-08-04
• [Presentation] Variable selection for historical functional linear models via the sparse regularization (2014)
  • Author(s): Matsui, H.
  • Organizer: The 3rd Institute of Mathematical Statistics Asia Pacific Rim Meeting
  • Place of Presentation: Howard International House
  • Year and Date: 2014-06-30 – 2014-07-03
• [Presentation] Selection of classification boundaries via the sparse regularization (2014)
  • Author(s): Matsui, H.
  • Organizer: 2014 Chinese Institute of Probability and Statistics Annual Meeting
  • Place of Presentation: National Dong Hwa University
  • Year and Date: 2014-06-27 – 2014-06-28
  • Invited
• [Presentation] ロジスティックモデルに対するスパース正則化 (2014)
  • Author(s): 松井秀俊，川野秀一
  • Organizer: 日本計算機統計学会第28回大会
  • Place of Presentation: 中央大学
  • Year and Date: 2014-05-17 – 2014-05-18
• [Presentation] スパース正則化を用いた繰り返し測定データの判別と変数選択 (2013)
  • Author(s): 松井秀俊
  • Organizer: 応用統計学会2013年度年次大会
  • Place of Presentation: パルセいいざか
• [Presentation] Variable selection for varying-coefficient models via the elastic net regularization (2013)
  • Author(s): Hidetoshi Matsui
  • Organizer: 2013 Joint Statistical Meetings
  • Place of Presentation: Palais des congres de Montreal
• [Presentation] 関数データに基づく回帰モデルの構築と正則化 (2013)
  • Author(s): 松井秀俊
  • Organizer: 2013年度統計関連学会連合大会
  • Place of Presentation: 大阪大学
• [Presentation] Variable selection for functional linear model via the sparse regularization (2013)
  • Author(s): Hidetoshi Matsui
  • Organizer: KSS/JSS/CSA International Session
  • Place of Presentation: Dongguk University
  • Invited
• [Presentation] スパース正則化を用いた判別境界の選択 (2013)
  • Author(s): 松井秀俊
  • Organizer: 研究集会「統計手法における近年の話題とその応用」
  • Place of Presentation: KKRホテル広島
• [Remarks] Hidetoshi Matsui
  • URL: https://sites.google.com/site/hidetoshimatsui/
• [Remarks] 九州大学-研究者情報
  • URL: http://hyoka.ofc.kyushu-u.ac.jp/search/details/K004601/index.html