| KANO Yutaka |  |
| Faculty of Culture and Information Science Department of Culture and Information Science | |
| Professor |
Last Updated :2024/05/23
Researcher Profile and Settings
researchmap
Research Interests
Research Areas
- Natural sciences / Applied mathematics and statistics
- Natural sciences / Basic mathematics
- Humanities & social sciences / Educational psychology
- Informatics / Statistical science
Research Experience
- Doshisha University, Faculty of Culture and Information Science, Professor, 2024/04 - Today
- Osaka University, 2024/04 -
- 武庫川女子大学, 社会情報学部, 教授（クロスアポイントメント）, 2022/04 - 2024/03
- 大阪大学, 数理・データ科学教育研究センター, センター長, 2022/04 - 2024/03
- Osaka University, Graduate School of Engineering Science,, 教授, 2004/04 - 2024/03
- Osaka University, Graduate School of Engineering Science,, Dean, 2017/04 - 2021/03
- 大阪大学 数理・データ科学教育研究センター, センター長, 2017/07 - 2019/06
- Osaka University,, Member of University Council, 2013/08 - 2017/03
- Osaka University, Faculty of Human Sciences,, Associete Professor, 1997/04 - 2004/03
- University of Tsukuba,, Institute of Mathematics,, Associete Professor, 1994/04 - 1997/03
- Osaka Prefectural University, 1990 - 1994
- Osaka University, 1987/10 - 1990/03
- Marine Technical College, 1984/04 - 1987/09
Education
- Doctor of Engineering, （大阪大学）, 1986/06 - 1986/06
- Osaka University, Graduate School of Engineering Science, 数理系専攻 博士後期課程 退学, 1983/04 - 1984/03
- Osaka University, Graduate School of Engineering Science, 数理系専攻 博士前期課程 修了, 1981/04 - 1983/03
- Osaka University, School of Science, Department of Mathematics, 1977/04 - 1981/03
Degree
Association Memberships
Committee Memberships
- President of the Behaviormetric Society, 2021/04 - 2027/03, The Behaviormetric Society, Society
- Psychometrka編集委員 Board of Trustee(理事), 2000 - 2003, 計量心理学会(Psychometric Society), Society, 計量心理学会(Psychometric Society)
- Journal of Multivariate Analysis,Associate Editor, 2002 - , Academic Press, Society, Academic Press
- 理事,欧文誌編集委員,欧文誌編集委員長, 1994 - 2000, 日本行動計量学会, Society, 日本行動計量学会
- 評議員,欧文誌編集委員, 1994 - 2000, 日本統計学会, Society, 日本統計学会
- 編集委員, 2000 - , 応用統計学会, Society, 応用統計学会
- 雑誌「数学(岩波書店)」常任編集委員, 1995 - , 日本数学会, Society, 日本数学会
- 欧文誌編集委員, 1995 - , 日本計算機統計学会, Society, 日本計算機統計学会
Awards
- 第23回 日本統計学会賞
Jun. 2018, 日本統計学会, Japan - 第29回 林知己夫賞（功績賞）
Sep. 2014, 日本行動計量学会, Japan - 第 7回 研究業績賞
Jun. 2013, 日本統計学会, Japan - 平成20年度 第2学期 共通教育賞（優れた授業を実践した教員）
May 2009, 大阪大学, Japan - 平成15年度 第1学期 共通教育賞（優れた授業を実践した教員）
Dec. 2003, 大阪大学, Japan - 第11回 小川研究奨励賞
Oct. 1997, 日本統計学会, Japan - 第12回 林知己夫賞（優秀賞）
Sep. 1997, 日本行動計量学会, Japan
Published Papers
- Causality and prediction in structural equation modeling: A commentary by Yutaka Kano on: “Which method delivers greater signal‐to‐noise ratio: Structural equation modeling or regression analysis with weighted composites?” by Yuan and Fang
Yutaka Kano
British Journal of Mathematical and Statistical Psychology, Wiley, 76(3) 679 - 681, 11 May 2023, Scientific journal - Bias reduction using surrogate endpoints as auxiliary variables
Yoshiharu Takagi; Yutaka Kano
Annals of the Institute of Statistical Mathematics, 71(4) 837 - 852, Dec. 2019, Scientific journal - Miss and Myth in the Analysis of Missing Data
Yutaka Kano
Journal of the Japan Statistical Society, 48(3) 199 - 214, Mar. 2019, Scientific journal - Meta analytical SEM: Equivalence between maximum likelihood and generalized least squares
Ke-Hai Yuan; Yutaka Kano
Journal of Educational and Behavioral Statistics, Sage, ASA, American Educational Research Association, 43(6) 639 - 720, Dec. 2018, Scientific journal - Missing Data Mechanisms and Homogeneity of Means and Variances–Covariances
Ke-Hai Yuan; Mortaza Jamshidian; Yutaka Kano
Psychometrika, Springer New York LLC, 83(2) 425 - 442, 01 Jun. 2018, Scientific journal - Identification problem of transition models for repeated measurement data with nonignorable missing values
Kosuke Morikawa; Yutaka Kano
Journal of Multivariate Analysis, Academic Press Inc., 165 216 - 230, 01 May 2018, Scientific journal - Semiparametric maximum likelihood estimation with data missing not at random
Kosuke Morikawa; Jae Kwang Kim; Yutaka Kano
CANADIAN JOURNAL OF STATISTICS-REVUE CANADIENNE DE STATISTIQUE, WILEY, 45(4) 393 - 409, Dec. 2017, Scientific journal - Identifiability of nonrecursive structural equation models
Mario Nagase; Yutaka Kano
STATISTICS & PROBABILITY LETTERS, ELSEVIER SCIENCE BV, 122 109 - 117, Mar. 2017, Scientific journal - Full information maximum likelihood estimation in factor analysis with a large number of missing values
Kei Hirose; Sunyong Kim; Yutaka Kano; Miyuki Imada; Manabu Yoshida; Masato Matsuo
JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION, TAYLOR & FRANCIS LTD, 86(1) 91 - 104, Jan. 2016, Scientific journal - Effect of Violation of the Normal Assumption on MI and ML Estimators in the Analysis of Incomplete Data
Shintaro Hojo; Michio Yamamoto; Yutaka Kano
COMMUNICATIONS IN STATISTICS-THEORY AND METHODS, TAYLOR & FRANCIS INC, 44(15) 3234 - 3250, 2015, Scientific journal - Likelihood Method in NMAR missingness
Yutaka Kano
Journal of the Japan Statistical Society, 43(2) 359 - 377, Mar. 2014, Scientific journal - A New Test on High-Dimensional Mean Vector Without Any Assumption on Population Covariance Matrix
Shota Katayama; Yutaka Kano
COMMUNICATIONS IN STATISTICS-THEORY AND METHODS, TAYLOR & FRANCIS INC, 43(24) 5290 - 5304, 2014, Scientific journal - Corrigendum to "A two sample test in high dimensional data" [J. Multivariate Anal. 114 (2013) 349-358]
Muni S. Srivastava; Shota Katayama; Yutaka Kano
Journal of Multivariate Analysis, 119 209 , Aug. 2013, Scientific journal - Asymptotic distributions of some test criteria for the mean vector with fewer observations than the dimension
Shota Katayama; Yutaka Kano; Muni S. Srivastava
JOURNAL OF MULTIVARIATE ANALYSIS, ELSEVIER INC, 116 410 - 421, Apr. 2013, Scientific journal - A two sample test in high dimensional data
Muni S. Srivastava; Shota Katayama; Yutaka Kano
Journal of Multivariate Analysis, Academic Press Inc., 114(1) 349 - 358, 2013, Scientific journal - A criterion-based model comparison statistic for structural equation models with heterogeneous data
Yun-Xian Li; Yutaka Kano; Jun-Hao Pan; Xin-Yuan Song
JOURNAL OF MULTIVARIATE ANALYSIS, ELSEVIER INC, 112 92 - 107, Nov. 2012, Scientific journal - Discovery of non-gaussian linear causal models using ICA
Shohei Shimizu; Aapo Hyvärinen; Yutaka Kano; Patrik O. Hoyer
CoRR, abs/1207.1413, 2012, Scientific journal - Analysis of NMAR missing data without specifying missing-data mechanisms in a linear latent variate model
Yutaka Kano; Keiji Takai
JOURNAL OF MULTIVARIATE ANALYSIS, ELSEVIER INC, 102(9) 1241 - 1255, Oct. 2011, Scientific journal - Test of independence in a 2 x 2 contingency table with nonignorable nonresponse via constrained EM algorithm
Keiji Takai; Yutaka Kano
COMPUTATIONAL STATISTICS & DATA ANALYSIS, ELSEVIER SCIENCE BV, 52(12) 5229 - 5241, Aug. 2008, Scientific journal - Does Structural Equation Modeling Outperform Traditional Factor Analysis, Analysis of Variance and Path Analysis ?
KANO Yutaka
Kodo Keiryogaku, The Behaviormetric Society of Japan, 29(2) 138 - 159, 2002 - Variable selection for structural models
Yutaka Kano
Journal of Statistical Planning and Inference, 108(3), 305-314, 2002 - Stepwise variable selection in factor analysis(jointly worked)
Yutaka Kano; Akira Harada
Psychometrika, 65 7 - 22, 2000 - Delta method approach in certain irregular condition
Yutaka Kano
Communications in Statistics - Theory and Methods, 28 789 - 807, 1999 - Beyond third-order efficiency
Yutaka Kano
Sankhy, 59(2) 179 - 197, 1997, Scientific journal - A note on robustness of two-stage procedure for a multivariate compounded normal distribution(jointly worked)
AOSHIMA M.
Sequential Anal., 16(2) 175 - 187, 1997 - Exploratory factor analysis with a common factor with two indicators
Kano Yutaka
Behaviormetrika, The Behaviormetric Society of Japan, 24(2) 129 - 145, 1997 - On averaging variables in a confirmqatory factor analysis model(jointly worked)
Ke-Hai Yuan; Peter M. Bentler; Yutaka Kano
Behaviormetrika, The Behaviormetric Society of Japan, 24(1) 71 - 83, 1997, Scientific journal - Third-order efficiency implies fourth-order efficiency
KANO Yutaka
Journal of the Japan Statistical Society, THE JAPAN STATISTICAL SOCIETY, 26(1) 101 - 117, 1996 - Fourth and fifth order efficiency: Fisher information
Yutaka Kano
Probability Theory and Mathematical Statistics(World Scientific), 193 - 200, 1996 - Identifiability of full, marginal, and conditional factor analysis models
Masamori Ihara; Yutaka Kano
Statistics and Probability Letters, 23(4) 343 - 350, 1995, Scientific journal - An asymptotic expansion of the distribution of Hotelling's T^2-statistic under general distributions
KANO Y.
Amer. J. Math. and Manage. Sci., 15(3-4) 317 - 341, 1995 - CONSISTENCY PROPERTY OF ELLIPTIC PROBABILITY DENSITY-FUNCTIONS
Yutaka KANO
JOURNAL OF MULTIVARIATE ANALYSIS, ACADEMIC PRESS INC JNL-COMP SUBSCRIPTIONS, 51(1) 139 - 147, Oct. 1994, Scientific journal - Identification of inconsistent variates in factor analysis
Yutaka Kano; Masamori Ihara
Psychometrika, Springer-Verlag, 59(1) 5 - 20, Mar. 1994, Scientific journal - Statistical Inference Based on Pseudo Maximum Likelihood Estimators in Elliptical Populations(jointly worked)
Yutaka Kano; Maia Berkane; Peter Bentler
Journal of the American Statistical Association, 88, 1993, Scientific journal - Robust statistics for test-of-independence and related structural models
Yutaka Kano
Statistics and Probability Letters, 15(1) 21 - 26, 03 Sep. 1992, Scientific journal - Asymptotic equivalence of unique variance estimators in marginal and conditional factor analysis models
Masamori Ihara; Yutaka Kano
Statistics and Probability Letters, 14(5) 337 - 341, 11 Jul. 1992, Scientific journal - Can test statistics in covariance structure model be trusted?
Litze Hu; Peter M. Bentler; Yutaka Kano
Psychological Bulletin, 112(2) 337 - 341, 1992, Scientific journal - THE ASYMPTOTIC-DISTRIBUTION OF A NONITERATIVE ESTIMATOR IN EXPLORATORY FACTOR-ANALYSIS
Y KANO
ANNALS OF STATISTICS, INST MATHEMATICAL STATISTICS, 19(1) 272 - 282, Mar. 1991, Scientific journal - COVARIANCE STRUCTURE-ANALYSIS WITH HETEROGENEOUS KURTOSIS PARAMETERS
Y KANO; M BERKANE; PM BENTLER
BIOMETRIKA, BIOMETRIKA TRUST, 77(3) 575 - 585, Sep. 1990, Scientific journal - NONITERATIVE ESTIMATION AND THE CHOICE OF THE NUMBER OF FACTORS IN EXPLORATORY FACTOR-ANALYSIS
Y KANO
PSYCHOMETRIKA, PSYCHOMETRIC SOC, 55(2) 277 - 291, Jun. 1990, Scientific journal - ON THE EQUIVALENCE OF FACTORS AND COMPONENTS
PM BENTLER; Y KANO
MULTIVARIATE BEHAVIORAL RESEARCH, LAWRENCE ERLBAUM ASSOC INC, 25(1) 67 - 74, Jan. 1990, Scientific journal - Comparative studies of non-iterative estimators based on ihara and kano’s method in exploratory factor analysis
Yutaka Kano
Communications in Statistics - Theory and Methods, 19(2) 431 - 444, 1990, Scientific journal - A new estimation procedure using G-inverse matrix in factor analysis
KANO Y.
Mathematica Japonica, 34(1) 43 - 52, 1989 - ON ASYMPTOTIC VARIANCES OF UNIQUENESS ESTIMATORS IN FACTOR-ANALYSIS
Y KANO; A SHAPIRO
SOUTH AFRICAN STATISTICAL JOURNAL, SOUTH AFRICAN STATISTICAL ASSOC, 21(2) 131 - 139, 1987, Scientific journal - A NEW ESTIMATOR OF THE UNIQUENESS IN FACTOR-ANALYSIS
M IHARA; Y KANO
PSYCHOMETRIKA, PSYCHOMETRIC SOC, 51(4) 563 - 566, Dec. 1986, Scientific journal - Consistency conditions on the least squares estimator in single common factor analysis model
Yutaka Kano
Annals of the Institute of Statistical Mathematics, Kluwer Academic Publishers, 38(1) 57 - 68, Dec. 1986, Scientific journal - Conditions on consistency of estimators in covariance structure model
Yutaka Kano
J. Japan Statist. Soc., 16(1) 75 - 80, 1986 - A condition for the regression predictor to be consistent in a single common factor model
Yutaka Kano
British Journal of Mathematical and Statistical Psychology, 39(2) 221 - 227, 1986, Scientific journal - Construction of additional variables conforming to a common factor model
Yutaka Kano
Statistics and Probability Letters, 2(4) 241 - 244, 1984, Scientific journal - Consistency of estimators in factor analysis.
Yutaka Kano
Journal of the Japan Statistical Society, 13(2) 137 - 144, 1983
MISC
- Missing of Data
Yutaka Kano; Miyuki Imada
電気情報通信学会誌, 100(11) 1274 - 1279, Nov. 2017 - An interpersonal sentiment quantification method applied to work relationship prediction
Miyuki Imada; Kei Hirose; Manabu Yoshida; Sun Yong Kim; Naoya Toyozumi; Guillaume Lopez; Yutaka Kano
NTT Technical Review, 15(3), Mar. 2017, Book review - CDO1-2 不完全データに対する情報量規準(一般セッション 数学・統計(1))
森川 耕輔; 伊森 晋平; 狩野 裕
日本行動計量学会大会発表論文抄録集, 日本行動計量学会, 43 66 - 67, 01 Sep. 2015 - Analysis of incomplete data
狩野 裕
生産と技術, 生産技術振興協会, 61(1) 71 - 76, 2009 - Consistency of penalized risk of boosting methods in binary classification
Kenichi Hayashi; Yasutaka Shimizu; Yutaka Kano
New Trends in Psychometrics, Universal Academic Press, Dec. 2008 - サポートベクターマシンにおけるモデル選択(一般セッション 統計理論)
梅原 武志; 狩野 裕
日本行動計量学会大会発表論文抄録集, 日本行動計量学会, 36 133 - 134, 02 Sep. 2008 - RMSEAの区間推定(一般セッション 多変量解析)
紺谷 幸弘; 狩野 裕
日本行動計量学会大会発表論文抄録集, 日本行動計量学会, 36 43 - 46, 02 Sep. 2008 - マルチスケールブートストラップ法による因子数の選択(一般セッション 統計理論)
高井 啓二; 紺谷 幸弘; 狩野 裕
日本行動計量学会大会発表論文抄録集, 日本行動計量学会, 36 131 - 132, 02 Sep. 2008 - 統計解析における数学のご利益と弊害(特別セッション 統計解析に数式はいるか?)
狩野 裕
日本行動計量学会大会発表論文抄録集, 日本行動計量学会, 36 249 - 250, 02 Sep. 2008 - 多項分析の推定について(セッションN-7(MK203) 一般セッション 数学・統計2)
高井 啓二; 狩野 裕
日本行動計量学会大会発表論文抄録集, 日本行動計量学会, 35 159 - 160, 02 Sep. 2007 - 因子分析モデルにおける共通性の区間推定 : 正規化変換によるアプローチ(セッションN-5(MK301) 一般セッション 数学・統計1)
紺谷 幸弘; 狩野 裕
日本行動計量学会大会発表論文抄録集, 日本行動計量学会, 35 109 - 112, 02 Sep. 2007 - SVM判別におけるモデル選択(セッションN-7(MK203) 一般セッション 数学・統計2)
梅原 武志; 狩野 裕
日本行動計量学会大会発表論文抄録集, 日本行動計量学会, 35 161 - 162, 02 Sep. 2007 - 単調な正規化変換とそれに基づく信頼区間の構成(数学・統計II)
紺谷 幸弘; 狩野 裕
日本行動計量学会大会発表論文抄録集, 日本行動計量学会, 34 196 - 199, Aug. 2006 - 統計的因果推論と因果探索. 第1回データマイニングと統計数理研究
狩野裕
SIG-DMSM, 2006 - SEMにおける因果同定の問題(因果は本当に証明できるのか?)
狩野 裕
日本行動計量学会大会発表論文抄録集, 日本行動計量学会, 33 342 - 343, 24 Aug. 2005 - A generalized least squares approach to blind separation of sources which have variance dependencies
Shohei Shimizu; Aapo Hyvarinen; Yutaka Kano
2005 IEEE/SP 13th Workshop on Statistical Signal Processing (SSP), Vols 1 and 2, IEEE, 2005 1009 - 1012, 2005 - 構造方程式モデリングにおける非正規性の利用(<一般セッション4>構造方程式モデル)(第31回 日本行動計量学会大会発表一覧)
清水 昌平; 狩野 裕
行動計量学, 日本行動計量学会, 31(2) 142 - 142, 10 Sep. 2004 - 情報処理教育におけるコンピュータ不安の分析 : 構造方程式モデリングによる因果推論と非正規性(<一般セッション4>構造方程式モデル)(第31回 日本行動計量学会大会発表一覧)
鳥居 稔; 清水 昌平; 狩野 裕
行動計量学, 日本行動計量学会, 31(2) 142 - 143, 10 Sep. 2004 - Nonnormal structural equation modeling
清水 昌平; 狩野 裕
日本行動計量学会大会発表論文抄録集, The Behaviormetric Society of Japan, 32 10 - 13, Sep. 2004 - S9-1 主成分分析は因子分析ではない!(特別セッション(S9) : 徹底討論「主成分分析versus因子分析」)(第30回日本行動計量学会大会発表一覧)
狩野 裕
行動計量学, 日本行動計量学会, 30(2) 240 - 240, 30 Jan. 2004 - G8-3 Analysis of Web access data with ICA
宮本 友介; 清水 昌平; 西川 康子; 狩野 裕
The Japanese Journal of Behaviormetrics, The Behaviormetric Society of Japan, 30(2) 235 - 235, 30 Jan. 2004 - 構造方程式モデルにおける指標の数はいくつであるべきか
狩野裕
日本行動計量学会, 行動計量学, The Japanese Journal of Behavior metrics, 日本行動計量学会, 31(2) 143 - 143, 2004 - Robustifing Covariance Selection via β-divergence
宮村 理; 狩野 裕
日本統計学会講演報告集, 71 505 - 506, 01 Sep. 2003 - 構造方程式モデルと因果(第78回行動計量シンポジウム「因果をめぐる統計アプローチ」)
狩野 裕
行動計量学, 日本行動計量学会, 30(1) 169 - 169, 29 Mar. 2003 - D-1 擬最尤法と識別性(統計モデル)(2003年度統計関連学会連合大会記録(日本統計学会第71回大会))
狩野 裕
日本統計学会誌, 日本統計学会, 33(3) 417 - 417, 2003 - Factor rotation and ICA(jointly worked)
Yutaka Kano; Shohei Shimizu; Yusuke Miyamoto
Proceedings of the Fourth International Symposium on ICA and BSS, 101 - 105, 2003, Introduction international proceedings - Rejoinder : Use of Error Convartances and the Role of Specific Factors
KANO Yutaka
The Japanese journal of behaviormetrics, The Behaviormetric Society of Japan, 29(2) 182 - 197, 25 Dec. 2002 - Independent component analysis for non-normal factor analysis(jointly worked)
In New Developments in Psychometrics (Yanai, H. et al., Eds.). Springer Verlag: Tokyo., 2002 - Use of SEM programs to precisely measure scale reliability
KANO Y.
New developments in psychometrics, Springer Verlag, 141 - 148, 2002 - 特別セッション(S17) 成長・発達データにおける多変量解析の効用と限界
無藤 隆; 狩野 裕
行動計量学, 日本行動計量学会, 27(2) 127 - 128, 31 Dec. 2000 - Towards Transition of the Statistics Paradigm : Statisticians Should Make Significant Collaborations with Applied Researchers
Kano Yutaka
Journal of the Japan Statistical Society, 日本統計学会, 30(3) 305 - 314, 2000 - Report on the IFCS-98 Rome
KANO Yutaka
Bulletin of the Computational Statistics of Japan, Japanese Society of Computational Statistics, 10(2) 166 - 167, 30 Oct. 1998 - 因子分析における変数選択 : 変数減少法
狩野 裕; 原田 章
日本統計学会講演報告集, 66 276 - 278, 01 Jul. 1998 - Improper solutions in exploratory factor analysis : Causes and treatments.
In Advances in Data Sciences and Classification(Eds Rizzi, A. , Vichi, M. And Bock, H. ), 375 - 382, 1998 - Selecting the number of components in a mixture of normal distributions : A simple case(Information and Statistical Inference)
Hatsuyama Mitsuji; Kano Yutaka; Nagao Hisao
RIMS Kokyuroku, Kyoto University, 916 131 - 148, Jul. 1995 - A NOTE ON THE CONJECTURE THAT THIRD-ORDER EFFICIENCY IMPLIES FOURTH-ORDER EFFICIENCY(Information and Statistical Inference)
KANO YUTAKA
RIMS Kokyuroku, Kyoto University, 916 112 - 130, Jul. 1995 - SELECTION OF VARIABLES IN FACTOR-ANALYSIS
M IHARA; Y KANO
PSYCHOMETRIC METHODOLOGY, GUSTAV FISCHER VERLAG, 171 - 176, 1993 - ASYMPTOTIC PROPERTIES OF STATISTICAL-INFERENCE BASED ON FISHER CONSISTENT ESTIMATORS IN THE ANALYSIS OF COVARIANCE-STRUCTURES
Y KANO
STATISTICAL MODELLING AND LATENT VARIABLES, ELSEVIER SCIENCE PUBL B V, 173-190 173 - 190, 1993 - Additional information and precision of estimators in multivariate structural models (jointly worked)
KANO Y.
Statistical Sciences and Data Analysis (VSP International Science Publishess), VSP International Science Publisher, 187-196 187 - 196, 1993 - Robustness of the Normal Theory Inference in Linear Latent Variate Models (統計数理研究所 研究活動 (研究会報告 多変量解析における潜在変数モデルの理論と応用))
狩野 裕
統計数理 = Proceedings of the Institute of Statistical Mathematics, 統計数理研究所, 39(1) 113 - 115, Jun. 1991 - COVARIANCE STRUCTURE-ANALYSIS UNDER A SIMPLE KURTOSIS MODEL
PM BENTLER; M BERKANE; Y KANO
COMPUTING SCIENCE AND STATISTICS, INTERFACE FOUNDATION NORTH AMERICA, 463 - 465, 1991 - Statistical inference in factor analysis: Recent developments
Yutaka Kano
Kodo Keiryogaku, The Behaviormetric Society of Japan, 18(1) 3 - 12, 1990, Introduction scientific journal
Books etc
- 新装版 AMOS, EQS, CALISによるグラフィカル多変量解析 : 目で見る共分散構造分析
狩野, 裕; 三浦, 麻子
現代数学社, Aug. 2020, Joint work - Handbook of Latent Variable and Related Models
Sik-Yum Lee
Elsevier, Jun. 2007, Contributor, Chapter 4. Selection of manifest variables - New Developments in Psychometrics
Yanai, H; Okada, A; Shigemasu, K; Kano, Y; Meulman, J
Springer, May 2003, Editor - （共編著）文科系の学生のための数学（上）（下）
ナカニシヤ出版, 2003 - 多変量解析の展開 -- 隠れた構造と因果を推理する
竹内啓 (編著), 2002, Joint work, 第2章 構造方程式モデリング、因果推論、そして非正規性 - Structural equation modeling for experimental data
Structural Equation Models : Present and future (A Festschrift in honor of Karl Joreskog) 381-402. SSI: Chicago., 2001
Research Projects
- Statistical Science of Bioinformatics
Kano Yutaka
We can summarize our research results as nine categories. In particular, results on the missing data analysis and meta analysis are influential. For the results to obtain, we have organized and offered five international symposiums and a domestic one in the research period. Each of the symposiums consisted of 3 to 20 presenters. In addition, we have hosted small size colloquiums 13 times in Osaka University, where totally 15 speakers were invited; and essential discussions in the colloquiums helped to proceed and complete our research., Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, 2015/04 -2019/03, Grant-in-Aid for Scientific Research (B), Osaka University - How serious is nonignorable missingness?
Kano Yutaka; TAKAI Keiji; OTSU Tatsuo; MORIKAWA Kosuke; IMADA Miyuki; TAKAGI Yoshiharu; NAGASE Mario; Kim Jae-Kwang; Yuan Ke-Hai; Jamshidian Mortaza(Mori)
Under NMAR missingness, the observed likelihood, without a missing-data mechanism, leads to a biased MLE. In this research, we developed a new methodology to express the bias of the MLE due to the missingness in closed form. Using the formula, we provided several mathematical conditions under which inclusion of auxiliary variables reduces or inflates the bias. The formula described above holds for any missing-data mechanism. This strong consequence can be proved because a shared-parameter model is taken for missingness. A final contribution of this research to be reported is to take a semi-parametric way to relax the strong condition required for the conventional missing-data analysis., Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, 2016/04 -2018/03, Grant-in-Aid for Challenging Exploratory Research, Osaka University - Comprehensive study of statistical evaluation methods based on various types of data
Iwasaki Manabu; KANO Yutaka; NAKANISHI Hiroko; WATANABE Michiko
In our research group, we set up "evaluation" as its core and carry out research on the theory and application of statistical analysis methods of various kinds in cooperating with researchers of various research fields such as medicine, education, quality control, information and so on. The results obtained were published at international symposiums and research meetings conducted during the research period. Also we published several books and many articles in international and domestic academic journals. As our main research result, we published theoretical results on statistical causal inference which is indispensable for the evaluation of statistical analysis results as a book and many articles as well. In addition, we examined the current state of statistical education in order to enhance statistical literacy of people, and discussed the issues among researchers and school teachers in various opportunities such as symposiums and research meetings., Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, 2013/10 -2017/03, Grant-in-Aid for Scientific Research (A), Seikei University - New developments of missing data analysis: NMARness and APB
Yutaka Kano; IWASAKI Manabu; TAKAI Keiji; OTSU Tatsuo; HIROSE Kei; KAMATANI Kengo; KIKUCHI Kenichi; Sobel Michael E.; Yuan Ke-Hai; Ricardo Silva; Mortaza Jamshidian; Aapo Hyvarinen
This research project has been completed by the two research groups conducted by Professor Yutaka Kano and Professor Manabu Iwasaki. We have offered research colloquiums several times for each year to advance the research project. The aim of the research project is to re-structure the theory of missing data analysis and to apply them to some statistical models for the analysis with missing data. Results of the project include mathematically weakening the MAR condition, defining NMARness and Approximate population Bias (APB) and studying mathematical properties of the NMARness and APB. Applying these theoretical results, we studied effectiveness of introducing auxiliary variables in several statistical models for the analysis of missing data. One particular result is to derive mathematical conditions under which introducing surrogate endpoints can reduce the bias of the MLE for data with possibly missing data at the endpoint., Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, 2013/04 -2016/03, Grant-in-Aid for Challenging Exploratory Research, Osaka University - Bayesian network structure learning when discrete and continuous variables are present.
Suzuki Joe; Washio Takashi; Kano Yutaka
We consider Bayesian network structure learning when discrete and continuous variables are present. The problem is rather hard and very few results are available. I particular, we had to assume that each continuous variable is Gaussian and no two discrete variable should be between a continuous variable. In this research, we mathematically prove consistency (the correct structure is estimated as the sample size increases). In particular, we proposed applications to independence testing and estimation of mutual information., Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, 2012/04 -2016/03, Grant-in-Aid for Scientific Research (C), Osaka University - Asymmetric and nonlinear statistical theory and its applications to economics and bioscience
TANIGUCHI Masanobu; YONEMOTO Kouji; HIRUKAWA Junichi; TAKAGI Yoshiji; HOSHINO Nobuaki; WANG Jin FANG; LIU Qing FENG; NAITO Kanta; SEKIYA Yuri; MATSUDA Shinichi; AKAHIRA Masafumi; TAKEMURA Akimichi; NISHIYAMA Yoshihiko; KANO Yutaka; AMANO Tomoyuki
We investigated a class of very general stochastic processes with nonlinear dynamics and asymmetric innovation distributions, which can be applied to a varitety of fields e.g., economics, finance, bionics, natural phenomenon etc., as a paradigm model. For them we developed the optimal inference based on LAN, and the empirical likelihood method to a class of stable processes. Shrinked estimation theory has been developed for stochastic processes. The theoretical results have been applied to estimation of portfolios, and the problem of causality. From the applications of the theoretical results, we have got some interesting feedback to mathematical theory. Also, in the process of research, we have raised young researchers., Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, 2011/04 -2015/03, Grant-in-Aid for Scientific Research (A), Waseda University - Statistical prediction, causation, incomplete data analysis and foundation of sciencee
KANO YUTAKA; DEGUCHI Yasuo; WASHIO Takashi; HAMAZAKI Toshimitsu; TAKAGI Yoshiji; SUGIMOTO Tomoyuki; TAKAI Keiji; NAITO Kanta; SHIMIZU Shohei; KATAYAMA Shota; YAMAMOTO Michio; SONG Xinyuan; JAMSHIDIAN Mortaza; HYVARINEN Aapo; YUAN Ke-hai
Analysis of incomplete data has been troublesome both theoretically and practically. In particular nonignorable missingness has been a serious issue in statistics. An alternative perspective of the theory of missing data analysis is to provide an insightful view of statistical causal inference. Some notable research outcomes include development of the analysis of doubly censored data, a new method of exploring causal structure for data with latent confounders via the LiNGAM approach, incomplete data analysis with a shared-parameter model and development of the EM algorithm with constraints., Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, 2010/04 -2014/03, Grant-in-Aid for Scientific Research (B), Osaka University - New Challenges for Statistics Education for Lifelong Learning in the Knowledge-based Society
WATANABE Michiko; YAMAGUCHI Kazunori; TAKEUCHI Akinobu; TAMURA Yoshiyasu; FUJII Yoshinori; AOYAMA Kazuhiro; SUENAGA Katsuyuki; MURAKAMI Masakatsu; ISHIOKA Tsunenori; TAKEMURA Akimichi; TAGURI Masaaki; KANO Yutaka; MINAMI Mihoko; SEO Takashi
Since the mid-1990s,in most of overseas countries,frameworks of statistics education through from primary and secondary to higher education have been reformed towards at cultivating students'statistical thinking as skills of problem-solving in daily lives. Through these processes various new concepts in curriculum, teaching methods,learning styles, teaching and learning materials and framework of assessment have been developed. In Japan,it is the stage that signs of the reform are appearing gradually in recent years. In this background, in this study we have studied on international comparison of statistics curriculums and developed original teaching and learning materials and a framework of learning assessment in Japanese that conform to the international standard. We also give a proposal for the next revision of national guideline on school curricula of statistical education., Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, 2009/04 -2014/03, Grant-in-Aid for Scientific Research (B) - Statistical regularization theory and neurophysiology
KANO Yutaka; KOBAYASHI Yasushi; INUI Toshiro; SHIMURA Tsuyoshi; ADACHI Kohei; MURATA Noboru; YAMAMOTO Michio
We organized and hosted an international symposium “Life Science and Statistics” in Osaka University in 2011, the first year of the research. The symposium was held to aim at constructing an interface among researchers in statistics, life science, cognitive psychologyand brain sciences. At least two joint international works have been accomplished, as fruits of having the symposium; one is on a new estimation of factor analysis model and the other on a new factor rotation method. After the symposium, a new research group of statisticians and brain scientists was created to conduct an interdisciplinary study., Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, 2011 -2012, Grant-in-Aid for Challenging Exploratory Research, Osaka University - Statistical Inference for High-Dimensional Data and Its Applications
SUGIYAMA Takakazu; FUJIKOSHI Yasunori; YAMAMOTO Taku; KAMAKURA Toshinari; KANO Yutaka; MURAKAMI Hidetoshi; TUKADA Shinnichi; TAKEDA Yuichi; SAKAORI Fumitake; KUNITOMO Naoto; KONISHI Sadanori
In multivariate analysis, it is important to develop the statistical method to analyze the high-dimensional data when the number of variables is large. In this study, we have also constructed a high-dimensional asymptotic theory for the traditional method when the number of variables is smaller than the number of observations. The aim of our study is to develop the introduction of high-dimensional method and the method of high-dimensional asymptotic theory when the number of variables is greater than the number of observations. We also applied our method and the statistical development of high-dimensional asymptotic theory in economics. More specifically, the challenges of the following, we have achievements. (1) Development of traditional multivariate methods for high-dimensional data (2) Development of modern multivariate methods for high-dimensional data (3) Development of high-dimensional modeling techniques (4) Research and the applications based on statistical simulation (5) Development and applications of high-dimensional statistical econometric, Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, 2009 -2011, Grant-in-Aid for Scientific Research (B) - Theory and Applications for Mathematical Methods in Statistical Science
TANIGUCHI Masanobu; YOSHIDA Nakahiro; OCHI Yoshimichi; YAO Feng; WAKAKI Hirofumi; KAKIZAWA Yoshihide; JIMBO Masakazu; MAESONO Nobuhiko; ANO Yutaka; HIRUKAWA Junichi; SHIMIZU Kunio; KONDO Masao; UNO Chikara; MIYATA Yoichi; TAKADA Yoshikazu; NOMAKUCHI Kentaro; KURIKI Shinji; KATO Takeshi; AKAHIRA Masafumi; TAKEMURA Akimichi; KONISHI Sadanori; TAKAHASHI Daisuke; MAEKAWA Koichi; SUZUKI Takeru; NISHII Ryuei; SASABUCHI Yoichi; AKI Shigeo; KURIKI Satoshi; AOSHIMA Makoto; TAMAKI Kenichiro; SHIRAISHI Hiroshi; SHIRAHATA Shingo; SHIOHAMA Takayuki
Mathematical models that describe random phenomena depending on past, present and future are called stochastic processes. In this research we established statistically optimal estimation theory for general stochastic processes, and applied the theoretical results to various fields, e.g., finance, economics, medical sciences, engineering and environment etc., yielding a lot of contributions. We performed the research with many foreign researchers as well as domestic ones, and developed young researchers., Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, 2007 -2010, Grant-in-Aid for Scientific Research (A), Waseda University - Integration of Latent Variables Models and Solutions to Practical Problems
SHIGEMASU Kazuo; HAEBARA Tomokazu; MAEKAWA Shinnichi; OHTSU Tatsuo; KANO Yutaka; OHMORI Takuya
Various Latent Variables Models were explained and integrated from the viewpoints of Bayesian Hierarchical Model, and Bayesian procedures appropriate to solve practical problems were proposed and applied to real data with success., Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, 2007 -2009, Grant-in-Aid for Scientific Research (B), The University of Tokyo - Development of Causal Structure Mining Method for Large Scale Dimensional Data and Construction of Gene Function Knowledge Base
WASHIO Takashi; KANO Yutaka; IMOTO Seiya; OHARA Kouzou; TERMIER Alexandlre; INOKUCHI Akihiro; SHIMIZU Shohei; KAWAHARA Yoshinobu
Scientists attempt to figure out function of each gene through the analysis of causal relations between gene expressions by using measurement data of the many gene expression variables (large scale dimensional data). However, the analysis of causal relations between dozens or hundreds of variables is hardly performed manually. In spite of this problem, the number of variables to which the computer based causal analysis is applicable is limited to 20-30 in the state of the art. Accordingly, this work developed a novel principle of the statistical causal analysis, and furthermore constructed a knowledge base of the functional relations among expressed genes for the scientists by using our developed approach., Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, 2007 -2009, Grant-in-Aid for Scientific Research (A), Osaka University - Comprehensive study on statistical causal inference
KANO Yutaka; YANAGIMOTO Takemi; YAMAMOTO Eiji; SATO Toshiya; KUMAGAI Etsuo; YAMAGUCHI Kazunori; WATANABE Michiko; MIYAKAWA Masami; KUROKI Manabu; SHIGEMASU Kazuo; UENO Maomi; MOTOMURA Yoichi; TODAYAMA Kazuhisa; ICHINOSE Masaki; DEGUCHI Yasuo; ADACHI Kohei; KARASAWA Kaori; HAEBARA Tomokazu; INUI Toshio; SEIYAMA Kazuo; SHIMIZU Yasutaka; MIYAMOTO Yusuke; ICHIKAWA Masanori; YANAGIHARA Hirokazu; NAITO Kanta
Active academic exchanges among researchers in statistical, informatics and social sciences, including philosophy of science in particular, have been made through hosting colloquiums of a few speakers regularly, symposiums of 10 to 15 talks several times a year, and international meetings. Some of our fruits obtained with the help of the governmental scientific research grant are i) a new robust methodology of the covariance selection, ii) a new method for determining direction of causation using nonnormality, ii) new estimation methods for data with nonignorable missing values in a 2 times 2 contingency table and a latent-variable model, and iii) clarification between conditional probability and scientific evidence., Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, 2006 -2009, Grant-in-Aid for Scientific Research (B), Osaka University - 共分散構造分析の数理的研究と応用的研究
科学研究費補助金, 1990 -2009, Competitive research funding - 統計的因果推論と非正規性
狩野 裕; 佐藤 俊哉; 山本 英二; 村田 昇; 足立 浩平; 宮川 雅巳
本企画調査では,統計的因果推論に関する国際会議開催のための内容的な調査打ち合せを行う. 因果とは何か,因果をどのように定義すべきか,(観察)データから事象間の因果関係がどこまで理解できるか,という基本的な問題は古くはギリシャ哲学でも議論されている.いま,経験科学の分野で,統計的因果推論に焦点が当てられている.しかしながら,それは,統計科学,数理統計学,人工知能,医学疫学,社会調査,教育学,心理学,(科学)哲学など多くの研究分野で個別に独立に議論されており,異分野間の情報交換がほとんどないといってよい.そこで,われわれは,個別分野で議論されてきた因果推論の諸問題を包括的に議論するため,平成19年度に各分野の一線級の研究者を招いた国際研究集会を開催する予定である.対象研究分野があまりに広範なため,会議を成功させるためには,各分野の研究者との事前の十分な内容的検討が欠かせない.以下に本研究に関する活動の概要を報告する. (1)2005年9月には「Statistical Causal Inference and Nonnormality」なる集会においてHyvarinen教授(フィンランド),Schafer教授(米国),星野崇広専任講師(東京大学),山口和範教授(立教大学)らをお招きし,国際会議について意見交換を行った. (2)2005年11月には「社会科学における因果とベイズアプローチ」なる集会において,戸田山和久教授(名古屋大学),植野真臣助教授(長岡技術科学大学),唐沢かおり助教授(名古屋大学)をお招きし,国際会議について意見交換を行った. (3)2006年12月には高田佳和教授(熊本大学)をお招きし,国際会議について意見交換を行った. (4)2006年1月には「ベイズ的方法による予測と因果分析」なる集会において,本村陽一研究員(産業技術総合研究所)駒木文保助教授(東京大学)をお招きし,国際会議について意見交換を行った. (5)2006年3月に東京大学において繁桝算男教授らと国際会議について意見交換を行った., 日本学術振興会, 科学研究費助成事業, 2005 -2005, 基盤研究(C), 大阪大学 - Between ICA and SEM
KANO Yutaka; KUROKI Manabu; SUGIMOTO Tomoyuki; HARADA Akira; SHIMADA Takahito; MURATA Noboru
(1) We have successfully introduced the ICA methodology of confirmatory nature and developed a new estimation method. These and related results were presented in IMPS2003 in Italy and in the annual meeting of the Behaviormetric Society of Japan in 2003. (2) We have proposed a new framework of Nonnormal SEM and applied it to the problem of statistical causal modeling. These and related results were presented in AIC30 in Yokohama and in the annual meeting of the Behaviormetric Society of Japan in 2003. (3) We organized an invited paper session entitled "Nonnormal Structural Equation Modeling" in IMPS2004 in California I myself chaired the session and gave a talk about "Between ICA and SEM." (4) We hosted an international symposium on ICA and SEM at the Nakanoshima Center in October in 2004. We had more than 80 participants. (5) We have studied specific structures on the mixing matrix in ICA in the analysis of risk and protective factors in criminal psychology. (6) In July of 2005, I gave an invited paper entitled "SEM and nonnormality" in the Netherlands in IMPS2005. (7) Using nonnormal information on data, we proposed a solution to the intrinsic problems of normal SEM such as no identifiable models, equivalent models, and saturate models. (8) We suggested to determine causal ordering of several nodes (observable variables) on the basis of ICA and path analysis of SEM., Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, 2003 -2005, Grant-in-Aid for Scientific Research (C), Osaka University - The Foundation of Mathematical Statistics on Quantum Inference and Its Applications
AKAHIRA Masafumi; AOSHIMA Makoto; HAYASHI Masato; YAMATO Hajime; KAGEYAMA Sanpei; MAESONO Yoshihiko
The statistical investigation on various themes was done as follows. (1) Involving a relationship between statistical models and statistics, the properties of the models were discussed and some interesting results on the behavior of various statistics are obtained. (2) In the theory of statistics to finance, time series and their applications, statistical procedures were shown to be asymptotically useful. (3) In the experimental design and its related area, the mathematical structure is clarified by combinatorial procedures, and results intended to apply to practical problems were obtained. (4) In statistical sequential inference, some sequential procedures were proposed, and their properties were discussed in details. The asymptotic efficiencies were shown. (5) The construction of mathematically fundamental theory of biostatistics is tried, and statistically inferential procedures are shown to play an important role. In particular, bioassay test, score test etc. were shown to be useful. (6) The relationship between non-locality in quantum mechanics and statistical inference is clarified, and inferential procedures is also shown to be efficient in quantum estimation and quantum test. Further, it is recognized to play an important role as the theoretical base of concrete physical phenomena. (7) In statistical inference, on the lower bound for tail probabilites of consistent estimators, the first and second order asymptotic efficiencies are investigated from a different viewpoint from conventional Bahadur efficiency. And in order to unify both of non-parametric and parametric tests, the mathematical setup was done, new test statistics based on estimators of spectral density matrics were proposed, and their asymptotic properties are derived. (8) Under a family of non-parametric quantum states, state estimation, prediction of quantum state, quantum information geometry and discrimination problem on quantum states are trated, and new interesting results were obtained. Many symposium on the above were held and active discussion and mutual exchange of information were also done. Their results were summarized as a volume., Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, 2002 -2005, Grant-in-Aid for Scientific Research (A), University of Tsukuba - 質問紙法による心理学的個人差測定尺度の構成の理論的・経験的基礎に関する研究
村上 隆; 狩野 裕; 金井 篤子; 村瀬 聡美; 平石 賢二; 高井 次郎
心理学の研究は,複数の心理学的概念間の因果関係を明らかにすることを目的にして行われる。研究の対象となる概念は,経験的な研究においては,変数として扱われる。その際,相関研究の果たす役割は大きい。相関研究とは,独立変数の値をランダムアサインメントによって割り当てることができる実験研究と異なり,独立変数の値が自然発生的な変動によって決まる個人差として与えられるような研究を指す。その結果,相関研究においては,概念間の因果関係の検討のために,理論への負荷が大きくなるだけでなく,統計的も複雑な手法が必要となる。さらに,各概念を表現していると考えられる変数上の個人差を,いかに信頼性と妥当性の高い尺度によって測定するかが,研究の成否を分ける重要なポイントとなる。 本研究は,心理学的な個人差測定尺度の構成のための理論と方法について,次の観点からの大規模な研究を実施するための企画・調査を目的として実施された。 (1)心理学的な相関研究において,測定に起因する問題にはどのようなものがあるか。 (2)現時点で用意されている統計学的,計量心理学的ツール・ボックスにある手法をどのように使えば,適切な尺度構成の方法となるのか? (3)新たに開発すべき手法が存在するとすれば,それはどのようなものでなければならないか? これらの賭問題について,研究代表者と分担者は,さまざまな形でコミュニケーションを繰り返してきた。その結果,つぎのプロジェクトにおいては, (1)経験的には,「不安」と「抑うつ」のような,概念的にも経験的にも十分に識別されないままできた概念の測定について,具体的な質問項目にもどり,かつ,明確な病理的属性をもつ被験者群を加えた検討が有効である。 (2)計量心理学的には,項目分析,主成分分析にもとづく古典的方法と,潜在方程式モデルの研究の諸段階における使い分けが必要であるが,そのための明確な基準はいまだ明らかでない。 (3)個人を単に次元上の点と見ない方法論が必要であり,そのヒントは,質的データの分析法である対応分析や,わが国独自の心理測定の方法であるSP表等にある。, 日本学術振興会, 科学研究費助成事業, 2004 -2004, 基盤研究(C), 名古屋大学 - A STUDY ON STATISTICAL INFERENCE OF STOCHASTIC PROCESS AND ITS ROBUSTNESS
INAGAKI Nobuo; SHIRAHATA Shingo; KANO Yutaka; KUMAGAI Etsuo; AKI Shigeo
Our aim of this study is to investigate the statistical inference of stochastic processes by their likelihood functions, especially for "exponential" stochastic processes and furthermore, to investigate the robust statistical inference for observations with additive outliers. The important mathematical structure of statistical inference is discussed by using the statistical informations in exponential stochastic processes. Our plan of this study is as follows : (1) We study the likelihood function of parametric models of stochastic process, especially exponential stochastic processes, and their statistical informations by the stochastic integral and Ito's formula. (2) We investigate 'the relationship between the statistical curvature and the information loss. (3) We study asymptotic methods in nonparametric and semi-parametric models and evaluates the performance of them by simulation experiments. (4) We study the first occurrence time of run and pattern in dependent sequence of bivariate observations. Our results of this research project are as follows : (1) We published the revise of "Mathematical Statistics" (in Japanese). (2) We write a paper "Exact information loss in multivariate gamma distribution" at Scientiae Mathematicae Japonicae (SCMJ) (2005). (3) We published a paper about a selection of models (2005) in press. (4) We write several papers about distributions of runs and patterns in dependent processes., Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, 2002 -2004, Grant-in-Aid for Scientific Research (C), OSAKA UNIVERSITY - 信頼性と因子分析
科学研究費補助金, 1997 -2003, Competitive research funding - Theory and applications of covariauce structure analysis
0032 (Japanese Only), 1997 -2003, Competitive research funding - Reliability and factor analysis
0091 (Japanese Only), 1997 -2003, Competitive research funding - "Confirmatory" independent component analysis and independent factor analysis
KANO Yutaka; ICHIKAWA Masanori; MURATA Noboru; HARADA Akira
(1) An international symposium on independent component analysis (ICA) and structural equation modeling (SEM) was held jointly with IMPS2001 at the Osaka University Convention Center in July 2001. We invited Professors A. Hyvarinen from Finland, P. M. Bentler from USA, Sik-Yum Lee from Hong Kong, A, Mooijaart from the Netherlands besides Japanese invited speakers. We discussed how we can incorporate the idea from confirmatory nature of SEM with the ICA field. (2) We showed that the model is not estimable where both specific factors and common factors influence on a dependent variable in the SEM framework and that the model can be estimated if the specific factors are mutually independent and nonnonnally distributed. The model is nothing a confirmatory ICA model. (3) It was shown that there are many models that are not estimable in the SEM framework but can be estimated within the ICA formulation if latent factors are nonnormal and independent. For instance, the exploratory factor analysis model with an arbitrary error structure is estimable if the errors are normally distributed. (4) We suggested a new goodness-of-fit test statistic of nonnormal structural models using higher-order moments., Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, 2000 -2002, Grant-in-Aid for Scientific Research (C), Osaka University - Researches on the Non-Regular Inference Theory and the Concepts of the Amounts of Information
AKAHIRA Masafumi; YOSHIDA Nakahiro; SHIRAISHI Takaaki; FUJIKOSHI Yasunori; KOIKE Ken-ichi; AOSHIMA Makoto
The statistical investigation on various themes was done as follows. (l)0n the statistical inference and its related topics, the inferential procedures were proposed and interesting results on the application were obtained. (2)0n the statistical non-regular theory, the properties of estimators were discussed, and new knowledges of the characterization of non-regular distributions were obtained. (3)0n the theory of inference and its information theoretic viewpoint, the structure of inference was clarified through amounts of information, and its relation to the theory of information was well investigated. (4)0n the fundamental theory to analyze the statistical model with prior informations and its applications, the optimality of inferential procedures was considered from the Bayesian point of view, and the results on possibility of the application to practical problems were obtained. (5)The space between multivariate analysis and time series was investigated in details, and new results on the comparison of inferential procedures were given. (6)0n the combinatoric design and its applications, the construction of experimental design was proposed and assessed. (7)0n the economic time series and mathematical finance, the construction of the fundamental theory of statistical inference was tried and its usefulness is investigated. (8)0n the multivariate analysis, the linear and non-linear models were discussed, and new results on the inference were obtained in the non-regular case which was regarded as a difficult one. (9)The theoretical fundamentals and its applications were well investigated from the viewpoint of sequential analysis, and new results on the inferential procedures were obtained in the case of non-regular distributions. (10)0n the statistical and mathematical anakysis, new results on the efficiency of estimation and test procedures were given. In addition to the above, the results on the statistical modeling and inference, the spatial statistics, the recent computer-assisted type inference and its applications and others were also obtained. Many symposiums on the above were held and active discussions and mutual exchanges of informations were also done. Their results were summarized as a book of about 800 pages., Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, 1998 -2001, Grant-in-Aid for Scientific Research (A), University of Tsukuba - Cross-Cultural Study of positive Interests toward the Sea
YOSHIDA Mitsuo; YAMADA Tsuneo; HARADA Akira; KANO Yutaka; SHINJI Reiko
In the present approach we studied human ecology, focusing on human beings as biological organisms and social beings in interaction with nature and their environment. The intention was to illuminate perceived environmental problems of contemporary human life cross-culturally. We assumed that the perception of human ecology varies systematically across culture and gender but also across time. Specifically, this study examined cultural and gender influences on attitudes, beliefs, opinions, and perceived risk factors in human ecology, furthermore on the level of knowledge about nature and environment, and finally on behavior affecting the environment. Subjects from Japan, Germany, Sweden, and the United States (total N=1,317) completed a survey scale consisting of seven components : 1) image of the sea, 2) image of the mountain, 3) image of the river, 4) sea affairs score, 5) environmental attitudes scale, 6) environmental knowledge scale, and 7) environmental behavior scale. Cultural differences revealed by the analyses included the following : 1) the Japanese group had the highest scores in environmental knowledge and the American the lowest, 2) the German and the Swedish participants described and evaluated their behavior as most and the Japanese as least protecting the environment., Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, 1998 -2000, Grant-in-Aid for Scientific Research (B). - Theoretical Research on Graphical Modeling and New Multivariate Analysis and the Development of the Software
NAGATA Yasushi; TSUBAKI Hiroe; KURIKI Satoshi; KANO Yutaka; MIYAKAWA Masami; NISHINA Ken
We studied the statistical multivariate analysis, especially the graphical modeling. The summary of theoretical research results is following : (1) multiplicity of tests and model selections ; (2) performance of deviance as a statistic for the validity of a model ; (3) a new variable selection procedure based on a path diagram ; (4) the effect of intervention on the independent variables using the directed model as a causal model ; (5) the performance of the conditional intervention ; (6) stepwise variable selection incovariance structure analysis ; (7) shrinkage estimation to smooth boundary ; (8) statistical aspect of process capability indices. The summary of the research results from practical view points is following : (1) the development and the improvement of a computer software for the graphical modeling of continuous variables ; (2) the development and the improvement of a computer software for the graphical modeling of the discrete wariables ; (3) the applied examples on the process control, remote sensing and customer satisfaction survey. We published the book "Introduction to graphical modeling" . This book was selected as the Nikkei Hinshitsukanri Bunkensho in 1999., Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, 1998 -1999, Grant-in-Aid for Scientific Research (C) - Is a model accepted in a small sample really better than a model rejected in a large sample?
KANO Yutaka; HARADA Akira; YOSHIDA Mitsuo
1. In this project, exploratory factor analysis model is considered. A suitable model is often rejected in a large sample in factor analysis, and then one usually increases in the number of factors. As a result, an improper solution is obtained. The ultimate aim of this project is to discuss whether the model rejected should be adopted in case when such a problem arises. For this we need to study causes of the improper solution. One fruit of this project on this respect is to suggest how to identify the cause of an improper solution and to find it useful in many real examples. This result was presented as an invited lecture at the IFCS1998 conference at Rome. 2. One possible cause of rejecting a suitable model in factor analysis is to include an variable inconsistent with the model considered. We suggest a new way of identifying an inconsistent variable with respect to a measure of goodness-of-fit. The result will be published in Psychometrika, an international journal on psychometrics. 3. The new way of the variable selection was programmed using JAVA and was open to public as a Web Page. We refer to the program as SEFA. 4. We held a workshop on SEFA in the annual meeting of the Japanese Psychological Society in 1999 to discuss usefulness of the program through applications to various fields of statistical oriented studies. Both a variable augmentation method and variable elimination method are described. It was shown that the variable elimination method is useful for exploratory purpose while the variable augmentation method is important for the case where there are some important variables that can not be eliminated in the research., Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, 1997 -1999, Grant-in-Aid for Scientific Research (C), Osaka University - Applying E-mail System for Human Sciences Students to their Computer Literacy and Psychology Education
YOSHIDA Mitsuo; HARADA Akira; YAMADA Tsuneo; KANO Yutaka; NAKAMURA Toshie
[1] Effective methods for computer literacy education -- Human sciences students are not usually skilled in computer, so they were classified into three classes according to their responses to on-line questionnaire items on computer literacy, and effective curriculums and teaching methods for every class are tried to find. [2] Lecture materials on Web pages -- The investigators have lectures and classes for experiments on Quantitative Psychology, Elementary Statistics, Multivariate Analysis and Music Psychology. Their lecture materials were composed on home pages written by HTML and in case of no facilities of networking, multimedia materials are constructed on CD-ROM. [3] On-line textbook -- An on-line Statistics textbook was written on Web pages and students are easy to access it, read pages, and answer the exercise questions by JavaScript programming. Although it takes some hours to learn the language, numerical calculation is easier than one by handy calculators. [4] Computer aided data analysis system -- All processes of documentation, such as writing sentences, numerical calculations, making figures and tables, and networking reference retrieval etc., especially statistical calculations, are performed in the same computer system, constructed by Lisp or JavaScript. [5] Visualized database of social surveys -- After social surveys conducted by the investigators' department, their results were preserved as database to be able to see the data structure visually. Some OOP (object-oriented programming) language such as LISP and JavaScript are easy to system construction., Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, 1995 -1997, Grant-in-Aid for Scientific Research (B), Osaka University - 小標本受容モデルversus大標本棄却モデル
狩野 裕; 小池 健一; 佐々木 建昭; 杉浦 成昭; 本橋 信義; 赤平 昌文
「標本数Nを十分大きくとると帰無仮説は必ず棄却される」という経験則がある.サイズαの検定は,帰無仮説H_0の下では,Nに関わらず100(1-α)%の確率でH_0を棄却しないはずである.しかしながら,標本数Nを十分大きくとれば,ほとんどの場合H_0は棄却される.仮説H_0を棄却したければNを十分大きくとってやればよいということになり,これはデータに基づく科学的判断ではなくなる.統計解析の誤用・悪用の一例である.このような問題はほとんどの仮説検定問題で起こる. 本研究では,モデルの適合度検定において上記問題を検定した.因子分析モデルの適合度検定は,母集団の共分散行列をΣとしてH_0 : Σ=ΛΛ'+Ψ versus H_1 : Σ is not restrictedとなる.H_0が棄却されないならばこのモデルはデータに矛盾しないと判断する.小標本(e.g.,N=100)の予備実験で因子分析モデルが上手く当てはまったが(小標本受容モデル),本格的に大標本(e.g.,N=2000)のデータをとり適合度検定を行うとモデルが棄却された(大標本棄却モデル).このようなことはしばしば見受けられ,研究者を困惑させる.統計家はもちろんこの事実を熟知している.統計家の解釈は次のようである.帰無仮説が棄却されないのは標本数N=100が小さすぎるからだ.検出力1-βを考慮の上検定法を再構築すべきである.また,N=2000は大標本だ.モデルが棄却されても仕方がない,N=2000でp-値がこの位だと適合度は悪くない.このように,検定結果をそのまま信用せず,標本数Nとの係わりのなかで過去の経験に頼り最終判断を下していることが多い.本研究では,このような熟達した統計家の経験に基づく判断を,何らかの意味で客観化するような数学的指標を構築することを目的として,以下の統計量を提案した. モデルは現実の近似でありデータは対立仮説から採られているという状況を考える.サイズαの検定においてγ(α<γ<1)を与え,次の量を定義する. N_<α,γ>=^H_0が確率γ以上で棄却される最小の標本数N N_<α,γ>は,ある意味で,真値の帰無仮説からの距離を表している.実際,N_<α,γ>が大きければ真値は帰無仮説に近く(従って大きな標本数が必要になる),小さければ帰無仮説から遠いことになる.適合度検定の場合はN_<α,γ>の大小でモデルの良さを計る,すなわち,N_<α,γ>が大きければ良いモデル,小さければ悪いモデル,ということになる. N_<α,γ>の推定方法としてbootstrap法を採用し,その近似がある意味でうまく行くことを数値実験により実証した.この研究成果を,9月に行われた日本行動計量学会年会にて発表した., 日本学術振興会, 科学研究費助成事業, 1996 -1996, 基盤研究(C), 筑波大学 - 絶対漸近有効性へ向かって
狩野 裕
最尤推定量(MLE)の3次(漸近)有効性はFisher により予想され Rao (1960)により証明された。証明の本質は1970年代に明らかにされた。5次の有効性の証明は最近、申請者によって、2乗リスク、集中確率、情報量という3種の基準の下で与えられた。 絶対漸近有効性に迫るためには、まず、5次有効性の証明の本質を明らかにしなければならない。本研究で明らかになった点は以下のとおりである。MLE が5次漸近有効であるという主張は、正確には正しくない。バイアス修正項に、MLE 以外の情報(補助情報)が使われているからである。なぜ、補助情報が必要なのであろうか。それは、漸近十分性の議論から、MLE は高次漸近十分ではないことが明らかにされており、この事実と対応する。つまり、高次十分統計量の具体的な利用の仕方、推定量の構成の仕方を与えたものが申請者の結果であった。 5次有効性の本質が明らかになったので、絶対漸近有効性の証明可能性はかなり現実味をおびてきたといえる。, 日本学術振興会, 科学研究費助成事業, 1995 -1995, 奨励研究(A), 筑波大学 - 数学の論理的構造
本橋 信義; 狩野 裕; 佐々木 建昭; 杉浦 成昭; 伊藤 光弘; 赤平 昌文
本研究の当初の目的は、本研究の研究代表者が提唱している新しい論理学の立場から、数学で実際に用いられている証明を分析し、数学の論理構造を明らかにすることであった。そこで具体的な命題Aの証明が与えられたと仮定して、その証明がどのように分析されるか眺めてみる。命題Aの正しさの証明は通常、次の形式をしている。 前提;「命題Bは正しい 推論;「命題Bから命題Aが導かれる。」 この推論の部分は、命題Aと命題Bを共通の主題(それをaとする)にかんして、ある条件(それぞれ、P(x)、Q(x)とすると) 命題Aは「主題aが条件P(x)をみたす。」という判断を 命題Bは「主題aが条件Q(x)をみたす。」という判断を表現しているとみなしたうえで上の推論は「条件P(x)が条件Q(x)の十分条件である。」という事実の証明になっている。 この場合、二つの命題AとBを共通の主題に関する条件として分解する事(これを命題の解釈という)が、証明の本質的な部分になるが、同じ命題に対して様々な解釈が有り得るため、多種多様な証明が生まれることになり、いろいろな数学の分野の特殊性が、その分野で扱う命題の解釈の型に反映されてくる。 また、うえの前提や推論自身もそれぞれ命題になるから、その正しさを示すためには、それぞれの前提と推論を示す必要が出てくる。このようにして、前提と推論の列が様々に生じることになる。これらの列の先頭に何がくるかは、その命題を扱う数学の理論に依存するが、最終的には、前提は公理や定義に、推論は、形式論理に吸収される。この具体的な型を分析できたことが本研究の最大の成果である。, 日本学術振興会, 科学研究費助成事業, 1994 -1994, 一般研究(B), 筑波大学 - 多変数複素解析学の研究
阪井 章; 宮崎 倫子; 狩野 裕; 原 惟行; 早川 款達郎; 長尾 壽夫
今年度は、多変数の複素解析のうち、とくに近似の問題とpeak setの問題を主として研究した。また、 近似の問題ではCarleman型の問題について研究し、次の結果を得た。1.R^nに関して対称な擬凸領域をGとするとき、R^nの開集合U=G∩R^nで連続な関数をGで正則な関数で一様近似できることを示した。Carlemanのswelling methodと関数環のanti‐symmetric setの方法を組み合わせたものである。2.C^nのtotally real set上の連続関数の整関数による一様近似について、近似可能条件である集合の定義関数のLevi‐formに関する条件を改良した。3.KがC^nの多項式凸なコンパクト集合の場合に、R^n×K上のCR関数の正則近似定理を証明した。swelling methodの他にGaussの関数の積分による方法も可能であることを示した。さらにKがコンパクトでない場合についても調べて、とくに、R^n×C^n場合には一般に近似不可能であることを示し、与えられたCR関数の満たすべき条件を導いた。4.C^nの多項式凸なtotally real set上の整関数による近似の可能性についての1つの条件を得た。これらの結果はそれぞれ論文として発表する予定である。 peak setの問題では、とくにpeak‐interpolation setについて研究した。滑らかな境界をもつ領域GについてはA^1(G)peak interpolation setが有限集合であることが知られているが、境界が滑らかでない場合、たとえば滑らかな境界をもつ強擬凸領域の共通部分のような場合には、有限でないpeak interpolation setが存在し得ることを示し、また、有限でないpeak interpolation setが存在するための一般的な条件を与えた。この結果は論文として発表の予定である。 近似の問題については一般のCR関数の大域的な近似の問題が、またpeak setの問題については、弱擬凸領域についての問題が今後の課題である。, 日本学術振興会, 科学研究費助成事業, 1993 -1993, 一般研究(C), 大阪府立大学 - 楕円分布と統計的推測
国際研究, 1989 -1993, Competitive research funding - Elliptical distribution and statistical inference
0064 (Japanese Only), 1989 -1993, Competitive research funding - 数値解析の基礎理論および関数方程式の数値近似解の解析への応用
早川 款達郎; 城崎 学; 狩野 裕; 原 惟行; 長尾 寿夫; 阪井 章
科学研究費補助を受けた本研究の課題は偏微分方程式・積分程式の数値近似解法の基礎研究であり、主に積分方程式の解析に数値解析的な側面から取組んだ。研究代表者のグループがとりあげたのは第1フレッドホルム型積分方程式である。この種の方程式は工学に直接現れるばかりでなく、偏微分方程式を境界要素法(BEM)等で解こうとする場合にも自然に現れる。BEMは自由境界問題等の解析に有力な道具を与え、また物質の表面構造や物体の境界面における現象の解析に関係の深い工学・応用数学の方面からその利用は常識となっている。 数学的に可解性がない(理論的にill-posed)ような一般の第1種フレッドホルム型積分方程式はさておき、工学上現れる積分方程式の多くは数学的にはwell-posedであるにもかかわらず、そのままの形では数値解析的にはill-posedになってしまうという困難がある。これを取扱易くするためには何等かの前処理が必要となる。 われわれは積分作用素をヴォルテラ型積分作用素の積に分解するという方法でこの前処理に一つの新たな方向を提案し、初期的な解答を与えた。数値線形代数からのアナロジイとしてこれをLU分解と呼ぶ。また研究分担者の他のグループはヴオルテラ型の微分積分方程式に対する数学的な解析を行ない様々な成果を得た。あるいは、関数の近似理論に関する複素関数からのアプローチや漸近理論への統計学からのアプローチ等数多くの論文発表や研究講演がなされた。 発表論文数(印刷中も含む) 14編 研究講演発表 17回 なお、研究代表者を含め研究分担者達はこれらの研究を行なうにあたり、各地の研究者のもとへ出向き、共同研究や討論を行なって、以上のような活発な成果をあげた。, 日本学術振興会, 科学研究費助成事業, 1992 -1992, 一般研究(C), 大阪府立大学 - 推定量のロバストネスの研究
長尾 壽夫; 小山 英之; 城崎 学; 狩野 裕; 早川 款達郎; 阪井 章
以前からある分布の中央値の推定について古伝的なものとして,標本の中央値で推定するので通常である。そこでその分散の推定量は,ジャックナイフ推定量では成功しない.そこでブ-ツストラップ法で求めると自然な推定量がEfronによって'79年に求められている.しかしこの推定量の結果はMart_3等によって8年に得られている。これはnyの標本に基づく経験分布関数の逆関数を用いて作られるものである。その逆関数は(0,1)区間をn等分した区間上で順序統計量が値としてある。そこで報告者は(0,1)区間をn等分するのではなく(0,1)上の一称分布で(n-1)ケの標本に基づく分割を行う.その関数の1/2の時の値の分散で中央値の分散を推定する.この考え方を平均を取ると分布の中央値の別の推定量が得られる.それは別型な順序統計量で,その係数は2項確率であたえられる.そこで古伝的なもに,マリツ等によるものと,2項係数によりもの3種類について,分布を標準正規分布,(-1/2,1/2)上の一称分布および指数分布の下で,平均目乘誤差を求め,ほぼ2項係数に基づくのが良いことがわかった。なお古典的なものは,通常良く用いられているにもかかわらず最も良くないことがわかった。また古典的な推定量の分散の推定についても同様の分布の下で計算を行ない2項係数に基づくのは悪くないことがわかった。 また共分散行例に関する検定の分布を一般の分布の下でその漸近展開を求めた.この結果は今までよく仮定された正規分布,だ円分布など含まれるが,例として多次元も分布の下でこれを求めた。その結果は簡学であり正規分布以外の分布での検定間の比較について新しい見地が見い出される可能性が得られた.また検定力の計算としてブ-ツストラップ法を用いて計算を行なった。, 日本学術振興会, 科学研究費助成事業, 1991 -1991, 一般研究(C), 大阪府立大学 - 確率システムに関する制御理論の研究
小山 英之; 城崎 学; 狩野 裕; 山縣 秀雄; 長尾 寿夫; 阪井 章
1.システム方程式が線形で2次の目的関数をもつ確率制御問題で表れる退化型の放物型偏微分方程式は厳密に解けることから、そこでなぜ異常性が表れないかを具体的に調べ、そこから異常性が表れないための条件を一般化するための手がかりを得つつある。さらに、この問題に関連する以下の結果を得た。 2.C^nの領域における正則関数の境界挙動、コンパクト集合の多項式凸性、閉集合上の連続関数の整関数による近似問題などを中心に研究した。これら3つの問題についてそれぞれ成果を得たので、それぞれ論文として作成し投稿中である。 3.正規分布を含む楕円分布をさらに含むより一般的な分布族を導入し、共分散構造解析の確率統計理論を展開した。, 日本学術振興会, 科学研究費助成事業, 1990 -1990, 一般研究(C), 大阪府立大学 - Experimental Study of Factor Analysis
MASASHI OKAMOTO; YUTAKA KANO; HIROSHI NAKAMICHI; TAKUO OHTA
This project is a continuation of the project "A theoretical and experimental study of factor analysis" supported by the Grant-in-Aid for Scientific Research (c), 1983-1984. In between the two projects the author published a book "Inshi-Bunseki no Kiso", JUSE Publ. 1986, and a survey paper "Recent developments in factor analysis" (ed. Suzuki ＆ Takeuchi, Quantitative Analysis in Social Sciences, Univ. Of Tokyo Press, 1987, Chap. 1). 1. Study of early-step estimators The author carried out a Monte Carlo experiment on early-step estimators obtained after a few (j) iterations starting from an initial value in order to reduce the estimation error due to an improper solution. A fixed loading model based on Emmett's data was abopted as a numerical model and the final estimator F was considered as a control. It was found that one-step estimator J(j=1) fared best. 2. Proposal of a random loading model and the number-of-factors problem A new construction method of the random loading model was proposed in order to evade an enevitable bias of the fixed loading model. It is determined by a few parameters and so is more objective than a fixed one. As methods to deal with the number-of-factors problem, Guttman-Kaiser method, likelihood ratio method and AIC method were compared with each other. On the whole, AIC method based on F was optimal. On the other hand, J was found better than F in reducing the estimation error of the unknown parameter. 3. Non-iterative estimator by Kano Kano proposed a method to obtain a non-iterative estimator using a g-inverse matrix. It has a merit of being consistent and seems to be worthy of further investigation., Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, 1987 -1988, Grant-in-Aid for General Scientific Research (C), Otemon Gakuen University