Updated on 2024/09/20

写真a

 
MAESONO Yoshihiko
 
Organization
Faculty of Science and Engineering Professor
Other responsible organization
Mathematics Course of Graduate School of Science and Engineering, Master's Program
Mathematics Course of Graduate School of Science and Engineering, Doctoral Program
Contact information
The inquiry by e-mail is 《here
Profile
昭和54年3月 九州大学理学部数学科卒業
昭和56年3月 九州大学大学院理学研究科数学専攻修了
昭和59年3月 九州大学大学院理学研究科数学専攻単位取得退学
昭和59年4月 鹿児島大学理学部助手
平成2年4月 九州大学教養部助教授
平成9年10月 九州大学経済学部助教授
平成15年4月 九州大学大学院経済学研究院教授
平成17年4月 九州大学大学院数理学研究院教授
平成31年4月 中央大学理工学部教授
External link

Degree

  • 理学博士 ( 九州大学 )

  • 理学修士 ( 九州大学 )

Education

  • 1984.3
     

    Kyushu University   doctor course   finished without a degree after completion of required course credits

  • 1981.3
     

    Kyushu University   master course   completed

  • 1979.3
     

    Kyushu University   graduated

  • 1975.3
     

    鹿児島県立指宿高等学校   graduated

Research History

  • 2019.4 -  

    中央大学理工学部教授

  • 2005.4 - 2019.3

    九州大学大学院数理学研究院教授

  • 2014.9    

    島根大学非常勤講師

  • 2012.10    

    鹿児島大学非常勤講師

  • 2006.3    

    筑波大学非常勤講師

  • 2005.4 - 2005.9

    福岡女子大学非常勤講師

  • 2003.4 - 2005.3

    九州大学大学院経済学研究院教授

  • 1997.10 - 2003.3

    九州大学経済学部経済工学科助教授

  • 2001.4 - 2001.9

    九州芸術大学芸術工学部非常勤講師

  • 1994.4 - 1997.9

    九州大学大学院数理学研究科助教授

  • 1990.4 - 1994.3

    九州大学教養部数学教室助教授

  • 1984.4 - 1990.3

    鹿児島大学理学部数学科助手

  • 1984 - 1990

    Kagoshima University

  • 1984 - 1990

    Research Associate, Kagoshima, University

  • Chuo University Faculty of Science and Engineering Department of Mathematics   教授

▼display all

Professional Memberships

  • RESEARCH ASSOSIATION OF STATISTICAL SCIENCES

  • Institute of Mathematical Statistics

  • 日本金融・証券計量・工学学会

  • Bernoulli Society

  • International Statistical Institute

  • Journal of the Korean Statistical Society

  • Annals of the Institute of Statistical Mathematics

  • Statistics

  • Bulletin Informatics and Cybernetics

  • ベルヌーイ協会

  • 応用統計学会

  • 国際数理統計学会(Institute of Mathemtical Statistics)

  • 日本統計学会

  • 日本数学会

▼display all

Research Interests

  • Nonparametric Statistics

  • Kernel Estimation

  • Asymptotic Theory

  • Nonparametric

  • kernel method

  • Asymptotic theory of statistical inference

  • Mathematical Statistics

  • 統計数学

Research Areas

  • Informatics / Statistical science  / Statistical science

  • Natural Science / Basic mathematics  / Foundations of mathematics/Applied mathematics

  • Natural Science / Applied mathematics and statistics  / Foundations of mathematics/Applied mathematics

Papers

  • Boundary-free kernel-smoothed goodness-of-fit tests for data on general interval

    Rizky Reza Fauzi, Yoshihiko Maesono

    Communications in Statistics: Simulation and Computation   2021

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Bellwether Publishing, Ltd.  

    We propose kernel-type smoothed Kolmogorov-Smirnov and Cramér-von Mises tests for data on general interval, using bijective transformations. Though not as severe as in the kernel density estimation, utilizing naive kernel method directly to those particular tests will result in boundary problem as well. This happens mostly because the value of the naive kernel distribution function estimator is still larger than 0 (or less than 1) when it is evaluated at the boundary points. This situation can increase the errors of the tests especially the second-type error. In this article, we use bijective transformations to eliminate the boundary problem. Some numerical studies illustrating the estimator and the tests’ performances will be presented in the last part of this article.

    DOI: 10.1080/03610918.2021.1894336

    Scopus

    researchmap

  • Conditional probability density and regression function estimations with transformation of data Reviewed

    Moriyama Taku, Maesono Yoshihiko

    Bulletin of Informatics and Cybernetics   52   1 - 25   2020

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Kyushu University  

    We propose a new kernel estimator of the conditional density function
    and discuss its asymptotic properties

    DOI: 10.5109/2558879

    researchmap

  • New type of gamma kernel density estimator Reviewed

    Rizky Reza Fauzi, Yoshihiko Maesono

    Journal of the Korean Statistical Society   49 ( 3 )   882 - 900   2020

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Springer  

    We propose new kernel type estimator of a density function, which reduce the boundary bias.

    DOI: 10.1007/s42952-019-00040-w

    researchmap

    Other Link: http://link.springer.com/article/10.1007/s42952-019-00040-w/fulltext.html

  • New kernel estimators of the hazard ratio and their asymptotic properties Reviewed

    MORIYAMA Taku, MAESONO Yoshihiko

    Annals of the Institute of Statistical Mathematics   2020

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • Asymptotci mean squared error of kernel estimator of excess distribution function Reviewed

    SHIMOKIHARA Atsushi, MAESONO Yoshihiko

    Bulletin of Informatics and Cybernetics   50   51 - 64   2018

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • Smoothed nonparametric tests and approximations of $p$-values Reviewed

    MAESONO Yoshihiko, MORIYAMA Taku, LU Mengxin

    Annals of the Institute of Statistical Mathematics   70   969 - 982   2018

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • Smoothed alternatives of the two-sample median and Wilcoxon's rank sum tests Reviewed

    MORIYAMA Taku, MAESONO Yoshihiko

    Statistics   52   1096 - 1115   2018

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • On direct kernel estimator of density ratio Reviewed

    MORIYAMA Masanari, MAESONO Yoshihiko

    Bulletin of Informatics and Cybernetics   50   27 - 42   2018

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • Error reduction for kernel distribution function estimators Reviewed

    Rizky Reza Fauzi, MAESONO Yoshihiko

    Bulletin of Informatics and Cybernetics   49   53 - 66   2017

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • Asymptotic properties of a kernel type estimator of a density ratio Reviewed

    MORIYAMA Taku, MAESONO Yoshihiko

    Bulletin of Informatics and Cybernetics   48   37 - 46   2016

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • On jackknife variance estimator for kernel density estimator and its application Reviewed

    NISHIMOTO Atsushi, MAESONO Yoshihiko

    Bulletin of Informatics and Cybernetics   47   1 - 9   2015

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • Edgeworth expansion for kernel estimators of a distribution function Reviewed

    HUANG Zhong, MAESONO Yoshihiko

    Bulletin of Informatics and Cybernetics   46   1 - 10   2014

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Research Association of Statistical Sciences  

    CiNii Books

    researchmap

  • Improved confidence intervals for quantiles Reviewed

    Yoshihiko Maesono, Spiridon Penev

    ANNALS OF THE INSTITUTE OF STATISTICAL MATHEMATICS   65 ( 1 )   167 - 189   2013.2

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:SPRINGER HEIDELBERG  

    We derive the Edgeworth expansion for the studentized version of the kernel quantile estimator. Inverting the expansion allows us to get very accurate confidence intervals for the pth quantile under general conditions. The results are applicable in practice to improve inference for quantiles when sample sizes are moderate.

    DOI: 10.1007/s10463-012-0369-6

    Web of Science

    researchmap

  • Improvement of normal approximation for kernel density estimator Reviewed

    Umeno Shota, MAESONO Yoshihiko

    Bulletin of Informatics and Cybernetics   45   11 - 24   2013

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Research Association of Statistical Sciences  

    CiNii Books

    researchmap

  • Edgeworth expansion for the kernel quantile estimator Reviewed

    Yoshihiko Maesono, Spiridon Penev

    ANNALS OF THE INSTITUTE OF STATISTICAL MATHEMATICS   63 ( 3 )   617 - 644   2011.6

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:SPRINGER HEIDELBERG  

    Using the kernel estimator of the pth quantile of a distribution brings about an improvement in comparison to the sample quantile estimator. The size and order of this improvement is revealed when studying the Edgeworth expansion of the kernel estimator. Using one more term beyond the normal approximation significantly improves the accuracy for small to moderate samples. The investigation is non- standard since the influence function of the resulting L-statistic explicitly depends on the sample size. We obtain the expansion, justify its validity and demonstrate the numerical gains in using it.

    DOI: 10.1007/s10463-009-0241-5

    Web of Science

    researchmap

  • Mean squared errors of bootstrap variance estimators for U-statistics Reviewed

    MIZUNO Masayuki, MAESONO Yoshihiko

    Bulletin of Informatics and Cybernetics   43   67 - 82   2011

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Research Association of Statistical Sciences  

    CiNii Books

    researchmap

  • Edgeworth Expansion and Normalizing Transformation of Ratio Statistics and Their Application Reviewed

    Yoshihiko Maesono

    COMMUNICATIONS IN STATISTICS-THEORY AND METHODS   39 ( 8-9 )   1344 - 1358   2010

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:TAYLOR & FRANCIS INC  

    Some statistics in common use take the form of a ratio of two statistics, such as sample correlation coefficient, Pearson's coefficient of variation, cumulant estimators, and so on. In this article, using an asymptotic representation of the ratio statistics, we will obtain an Edgeworth expansion and a normalizing transformation with remainder term o(n-1/2). The Edgeworth expansion is based on a Studentized ratio statistic, which is studentized by a consistent variance estimator. Applying these results to the sample correlation coefficient, we obtain the normalizing transformation and an asymptotic confidence interval of the correlation coefficient without assuming specific underlying distribution. This normalizing transformation is an extension of the Fisher's z-transformation.

    DOI: 10.1080/03610920802311741

    Web of Science

    researchmap

  • 高次モーメントのノンパラメトリック推定 Reviewed

    前園 宜彦

    日本統計学会誌   39   355 - 367   2009

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • An Edgeworth expansion and a normalizing transformation for L-statistics Reviewed

    MAESONO Yoshihiko

    Bulletin of Informatics and Cybernetics   39   25 - 43   2007

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Research Association of Statistical Sciences  

    CiNii Books

    researchmap

  • Higher-order comparisons of asymptotic confidence intervals Reviewed

    Y Maesono

    JOURNAL OF STATISTICAL PLANNING AND INFERENCE   133 ( 2 )   359 - 379   2005.8

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:ELSEVIER SCIENCE BV  

    This paper presents discussion of properties of asymptotic confidence intervals based on a normalizing transformation and a Cornish-Fisher inversion of a studentized statistic. The normalizing transformation discussed herein removes bias, skewness and kurtosis. The Cornish-Fisher inversion is obtained from the Edgeworth expansion of the studentized statistic with residual term o(n(-1)). Asymptotic mean-squared errors and simulation results are also discussed. (c) 2004 Elsevier B.V. All rights reserved.

    DOI: 10.1016/j.jspi.2004.02.009

    Web of Science

    researchmap

  • Asymptotic representations of ratio statistics and their mean squared errors Reviewed

    MAESONO Yoshihiko

    Journal of the Japan Statistical Society   35   73 - 97   2005

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • An Edgeworth expansion of a convex combination of $U$-statisitics based on studentization Reviewed

    YAMATO Hajime, TODA Koichiro, NOMACHI Toshifumi, MAESONO Yoshihiko

    Bulletin of Informatics and Cybernetics   36   105 - 130   2004.12

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Research Association of Statistical Sciences  

    CiNii Books

    researchmap

  • Asymptotic representations of skewness estimators of studentized $U$-statistics. Reviewed

    MAESONO Yoshihiko

    Bulletin of Informatics and Cybernetics   36   91 - 104   2004.12

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Research Association of Statistical Sciences  

    CiNii Books

    researchmap

  • Higher order normalizing transformations of asymptotic U-statistics for removing bias, skewness and kurtosis Reviewed

    Y Fujioka, Y Maesono

    JOURNAL OF STATISTICAL PLANNING AND INFERENCE   83 ( 1 )   47 - 74   2000.1

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:ELSEVIER SCIENCE BV  

    This paper proposes a normalizing transformation which removes bias, skewness and kurtosis, simultaneously. Its convergence rate to the standard normal distribution is o(n(-1)). The transformation is polynomial and monotone. We consider a class of asymptotic U-statistics, which includes most of interesting statistics. (C) 2000 Elsevier Science B.V. All rights reserved. MSC: primary 62G20; secondary 62E20.

    Web of Science

    researchmap

  • A weighted bootstrap approach to bootstrap iteration Reviewed

    P Hall, Y Maesono

    JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY   62 ( 1 )   137 - 144   2000

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:BLACKWELL PUBL LTD  

    The operation of resampling from a bootstrap resample, encountered in applications of the double bootstrap, may be viewed as resampling directly from the sample but using probability weights that are proportional to the numbers of times that sample values appear in the resample. This suggests an approximate approach to double-bootstrap Monte Carlo simulation, where weighted bootstrap methods are used to circumvent much of the labour involved in compounded Monte Carlo approximation. In the case of distribution estimation or, equivalently, confidence interval calibration, the new method may be used to reduce the computational labour. Moreover, the method produces the same order of magnitude of coverage error for confidence intervals, or level error for hypothesis tests, as a full application of the double bootstrap.

    Web of Science

    researchmap

  • On the normal approximations of a studentized symmetric statistic Reviewed

    MAESONO Yoshihiko

    Mathematica Japonica   50   433 - 449   1999

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • Asymptotic comparisons of several variance estimators and their effects for studentizations Reviewed

    Y Maesono

    ANNALS OF THE INSTITUTE OF STATISTICAL MATHEMATICS   50 ( 3 )   451 - 470   1998.9

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:KLUWER ACADEMIC PUBL  

    In this paper we obtain asymptotic representations of several variance estimators of U-statistics and study their effects for studentizations via Edgeworth expansions. Jackknife, unbiased and Sen's variance estimators are investigated up to the order o(p)(n(-1)). Substituting these estimators to studentized U-statistics, the Edgeworth expansions with remainder term o(n(-1)) are established and inverting the expansions, the effects on confidence intervals are discussed theoretically. We also show that Hinkley's corrected jackknife variance estimator is asymptotically equivalent to the unbiased variance estimator up to the order o(p)(n(-1)).

    Web of Science

    researchmap

  • Higher order relations between Cornish-Fisher expansions and inversions of saddlepoint approximations Reviewed

    MAESONO Yoshihiko, PENEV Spiridon

    Journal of the Japan Statistical Society   28 ( 1 )   21 - 38   1998

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:THE JAPAN STATISTICAL SOCIETY  

    Many numerical examples have demonstrated that the saddlepoint approximation for the cumulative distribution function of a general normalised statistic behaves better in comparison with the third order Edgeworth expansion. This effect is especially pronounced in the tails. Here we are dealing with the inverse problem of quantile evaluation. The inversion of the Lugannani-Rice approximation is compared with the Cornish-Fisher expansion both theoretically and numerically. We show in a very general setting that the expansion of the inversion of the Lugannani-Rice approximation up to third order coincides with the Cornish-Fisher expansion. Based on this, an explanation of the superiority of the former in comparison with the latter in the tails and for small samples is given. An explicit approximation of the inversion of the Lugannani-Rice formula is suggested that utilizes the information in the cumulant generating function and improves upon the Cornish-Fisher formula.

    DOI: 10.14490/jjss1995.28.21

    researchmap

  • Asymptotic properties of jackknife skewness estimators and Edgeworth expansions Reviewed

    MAESONO Yoshihiko

    Bulletin of Informatics and Cybernetics   30 ( 1 )   51 - 68   1998

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Research Association of Statistical Sciences  

    CiNii Books

    researchmap

  • Mean square errors of variance estimators and their Edgeworth expansions Reviewed

    MAESONO Yoshihiko

    Journal of the Japan Statistical Society   28 ( 1 )   1 - 19   1998

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:THE JAPAN STATISTICAL SOCIETY  

    This paper studies the variance estimators for a class of U-statistics. We obtain asymptotic representations of jackknife, Hinkley's (1978) corrected jackknife, unbiased, Sen's (1960), and new variance estimators. The asymptotic mean square errors of these estimators are theoretically investigated. The Edgeworth expansions of the estimators with remainder term o(n-1) are also established. We show that the normalized Hinkley's corrected estimator coincides with the normalized unbiased estimator up until the order n-1/2op(n-1).

    DOI: 10.14490/jjss1995.28.1

    researchmap

  • An asymptotic representation of a ratio of two statistics and its applications Reviewed

    Y Maesono

    COMMUNICATIONS IN STATISTICS-THEORY AND METHODS   27 ( 2 )   305 - 327   1998

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:MARCEL DEKKER INC  

    Some statistics in common use take a form of a ratio of two statistics. In this paper, we will discuss asymptotic properties of the ratio statistic. We obtain an asymptotic representation of the ratio with remainder term o(p)(n(-1)) and a Edgeworth expansion with remainder term o(n(-1/2)). And as example, the asymptotic representation and the Edgeworth expansion of the jackknife skewness estimator for U-statistics are established and we discuss the biases of the skewness estimator theoretically. We also apply the result to an estimator of Pearson's coefficient of variation and the sample correlation coefficient.

    Web of Science

    researchmap

  • Edgeworth expansions of a studentized U-statistic and a jackknife estimator of variance Reviewed

    Y Maesono

    JOURNAL OF STATISTICAL PLANNING AND INFERENCE   61 ( 1 )   61 - 84   1997.5

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:ELSEVIER SCIENCE BV  

    We obtain the H-decomposition of a jackknife estimator of the variance of U-statistic and derive an Edgeworth expansion with remainder term o(n(-1/2)). We also obtain an approximation of a studentized U-statistic substituting the jackknife estimator of the variance. An Edgeworth expansion with remainder term o(n(-1)) is established for the studentized U-statistic with arbitrary degree of the kernel.

    Web of Science

    researchmap

  • An Edgeworth expansion of a linear combination of U-statistics Reviewed

    MAESONO Yoshihiko

    Journal of the Japan Statisticul Society   26   177 - 195   1996

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • A note on biases of jackknife estimators of third central moments Reviewed

    Y Maesono

    COMMUNICATIONS IN STATISTICS-THEORY AND METHODS   25 ( 8 )   1931 - 1942   1996

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:MARCEL DEKKER INC  

    In this paper we study the biases of jackknife estimators of central third moments which play an important role in improving the accuracy of the normal approximation. It has been found in simulation studies that the jackknife estimator of the skewness coefficient, into which the jackknife variance and third moment estimators are substituted, have downward biases. For the jackknife variance estimators, their asymptotic properties are precisely studied and their biases are discussed theoretically. Here we study the biases of the jackknife estimators of the central third moments for U-statistics theoretically. The results show that the biases are not always downward.

    Web of Science

    researchmap

  • Edgeworth expansions for functionals of U-statistics Reviewed

    Yoshihiko Maesono

    Kyushu Journal of Mathematics   50 ( 2 )   311 - 334   1996

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    DOI: 10.2206/kyushujm.50.311

    Scopus

    researchmap

  • Higher order comparisons of jackknife variance estimators Reviewed

    Yoshihiko Maesono

    Journal of Nonparametric Statistics   7 ( 1 )   35 - 45   1996

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Taylor and Francis Inc.  

    In this paper we discuss jackknife estimators of the variance and their corrections precisely. Shao-Wu [10] have studied a jackknife variance estimator which is based on a delete-d-original estimator. And they have proved the consistency of the delete-d jackknife variance estimator even if the original estimator is not smooth. Their results are especially useful for the jackknife estimation of the variance of the sample quantile. Whereas in the case of smooth original estimators, which include U-statistics, the delete-d jackknife variance estimator is at least as large as the delete-1 estimator which is the traditional jackknife variance estimator. Then the delete-d jackknife variance estimator has larger bias than the delete-1.

    DOI: 10.1080/10485259608832687

    Scopus

    researchmap

  • On the normal approximations of a studentized U-statistics Reviewed

    MAESONO Yoshihiko

    Journal of the Japan Statistical Society   25 ( 19 )   19 - 33   1995

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    DOI: 10.14490/jjss1995.25.19

    researchmap

  • ON THE NORMAL APPROXIMATIONS OF V-STATISTICS AND L-STATISTICS Reviewed

    Y MAESONO

    JOURNAL OF STATISTICAL PLANNING AND INFERENCE   42 ( 3 )   291 - 314   1994.12

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:ELSEVIER SCIENCE BV  

    The rates of convergence to the normal distribution are investigated for V- and L-statistics. We derive an inequality which gives a lower bound of the uniform distance between two distributions of the V-statistic and the normal distribution. We obtain an inequality which gives a lower bound of the uniform distance, and is meaningful in the case that the distribution of the standardized V-statistic is symmetric around the origin. Further, we also derive similar inequalities for the L-statistic. The proofs are based on Stein's method.

    Web of Science

    researchmap

  • U-statistics and related topics Invited Reviewed

    MAESONO Yoshihiko, YAMATO Hajime

    Sugaku Expositions   7   43 - 57   1994

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • U-statistics and related fopics

    Sugaku Expositions   7 ( 43 )   1994

     More details

  • ON THE NORMAL APPROXIMATION OF U-STATISTICS OF DEGREE-2 Reviewed

    Y MAESONO

    JOURNAL OF STATISTICAL PLANNING AND INFERENCE   27 ( 1 )   37 - 50   1991.1

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:ELSEVIER SCIENCE BV  

    The rates of convergence to the normal distribution are investigated for U-statistics of degree two. We derive an inequality which gives a lower bound for the uniform distance between the distribution of a U-statistic and the standard normal distribution, and which is useful in the case where the distribution of U-statistic is symmetric around the orgin. The proof is based on Stein's method.

    Web of Science

    researchmap

  • U-statistics and related topics Invited Reviewed

    MAESONO Yoshihiko, YAMATO Hajime

    Iwanami Sugaku   43 ( 3 )   205 - 216   1991

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    DOI: 10.11429/sugaku1947.43.205

    CiNii Books

    researchmap

    Other Link: https://jlc.jst.go.jp/DN/JALC/00384238747?from=CiNii

  • ESTIMATION UNDER INVARIANT DISTRIBUTIONS Reviewed

    H YAMATO, Y MAESONO

    JOURNAL OF STATISTICAL PLANNING AND INFERENCE   22 ( 1 )   55 - 61   1989.5

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:ELSEVIER SCIENCE BV  

    Web of Science

    researchmap

  • DEFICIENCIES OF U-STATISTICS OF DEGREE-2 UNDER SYMMETRIC DISTRIBUTIONS Reviewed

    H YAMATO, Y MAESONO

    COMMUNICATIONS IN STATISTICS-THEORY AND METHODS   18 ( 1 )   53 - 66   1989

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:MARCEL DEKKER INC  

    Web of Science

    researchmap

  • LOWER BOUNDS FOR THE NORMAL APPROXIMATION OF A SUM OF INDEPENDENT RANDOM VARIABLES Reviewed

    Yoshihiko Maesono

    Australian Journal of Statistics   31 ( 3 )   475 - 485   1989

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    The rates of convergence to the normal distribution are investigated for a sum of independent random variables. Using Stein's method, we derive a lower bound of the uniform distance between two distributions of independent sum and normal. Copyright © 1989, Wiley Blackwell. All rights reserved

    DOI: 10.1111/j.1467-842X.1989.tb00991.x

    Scopus

    researchmap

  • A lower bound for the normal approximation of U-statistics Reviewed

    Y. Maesono

    Metrika: International Journal for Theoretical and Applied Statistics   35 ( 1 )   255 - 274   1988

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    In this paper, the rates of convergence to the normal distribution are investigated for U-statistics. Using Stein’s method, we derive a lower bound of the uniform distance between the distributions of U-statistics and the standard normal distribution. © 1988, Physica-Verlag Ges.m.b.H. All rights reserved.

    DOI: 10.1007/BF02613314

    Scopus

    researchmap

  • COMPETITORS OF THE WILCOXON SIGNED RANK TEST Reviewed

    Y MAESONO

    ANNALS OF THE INSTITUTE OF STATISTICAL MATHEMATICS   39 ( 2 )   363 - 375   1987

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:KLUWER ACADEMIC PUBL  

    Web of Science

    researchmap

  • Edgeworth expansion for one-sample U-Statistics Reviewed

    MAESONO Yoshihiko

    Bulletin of Informations and Cybernetics   22 ( 3-4 )   189 - 197   1987

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • INVARIANT U-STATISTICS Reviewed

    H YAMATO, Y MAESONO

    COMMUNICATIONS IN STATISTICS-THEORY AND METHODS   15 ( 11 )   3253 - 3263   1986

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:MARCEL DEKKER INC  

    Web of Science

    researchmap

  • CHARACTERIZATION OF PROBABILITY-MODELS BY AN ODDS RATIO IN PROSPECTIVE AND RETROSPECTIVE STUDIES Reviewed

    T YANAGAWA, K NOMAKUCHI, Y MAESONO

    COMMUNICATIONS IN STATISTICS-THEORY AND METHODS   15 ( 8 )   2347 - 2353   1986

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (scientific journal)   Publisher:MARCEL DEKKER INC  

    Web of Science

    researchmap

  • Semi-parametric method and its efficiency in the analysis of a case-control study Reviewed

    MAESONO Yoshihiko, YANAGAWA Takashi

    Memoirs of the Faculty of Science. Kyushu University. Series A. Mathematics   40 ( 1 )   19 - 30   1986

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Kyushu University  

    The asymptotic normality under the null hypothesis and also under a contiguous alternative is explored for the semi-parametoric method in a multiply matched case-control study in a context of testing statistical hypothesis. The Pitman efficiency of the method is compared with the tests from the classical approach in a framework of a location and scale parameter models. It is shown that the method could lose substantial efficiency when the underlying distribution is normal.

    DOI: 10.2206/kyushumfs.40.19

    CiNii Books

    researchmap

    Other Link: https://jlc.jst.go.jp/DN/JALC/00297738235?from=CiNii

  • Over-all rank tests for 1 to k matched continuous data in case-control studies Reviewed

    YANAGAWA Takashi, MAESONO Yoshihiko

    Memoirs of the Faculty of Science. Kyushu University. Series A. Mathematics   38 ( 1 )   75 - 89   1984

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Kyushu University  

    Over-all rank tests, for continuous data, are developed in order to combine individual test results in pairwise comparisons between cases and each of k control groups in a 1 to k matched design in case-control studies. Although the over-all-tests do not always have higher efficiencies than some tests which do not have the over-all-function, it is shown that the loss of efficiency would not be considerable.

    DOI: 10.2206/kyushumfs.38.75

    CiNii Books

    researchmap

    Other Link: https://jlc.jst.go.jp/DN/JALC/00300484050?from=CiNii

▼display all

Books

  • Statistical inference based on kernel distribution function estimators

    Fauzi, Rizky Reza, 前園, 宜彦( Role: Joint author)

    Springer  2023.6  ( ISBN:9789819918614

     More details

    Total pages:viii, 96 p.   Language:English  

    researchmap

  • ノンパラメトリック統計

    前園 宜彦( Role: Sole author)

    共立出版  2019.10 

     More details

  • Quick study of probability and statistics

    ( Role: Sole author)

    サイエンス社  2018.10 

     More details

    Language:Japanese   Book type:Textbook, survey, introduction

    researchmap

  • 詳解演習 確率統計

    前園 宜彦( Role: Sole author)

    サイエンス社  2010.11 

     More details

  • 概説 確率統計(2版)

    前園 宜彦( Role: Sole author)

    サイエンス社  2009.9 

     More details

  • Asymptotic theory of statistical inference

    ( Role: Sole author)

    九州大学出版  2001.10 

     More details

    Language:Japanese   Book type:Scholarly book

    researchmap

▼display all

MISC

  • ノンパラメトリックなハザード比推定のバイアス修正について

    森山卓, 前園宜彦

    統計関連学会連合大会講演報告集   2018   2018

  • 二標本ノンパラメトリック検定の連続化と有意確率の近似について

    森山卓, 前園宜彦

    統計関連学会連合大会講演報告集   2015   2015

  • ノンパラメトリック検定統計量の有意確率と連続化統計量について

    前園宜彦, 森山卓

    統計関連学会連合大会講演報告集   2014   2014

  • Nonparametric confidence intervals based on asymptotic expansions

    Discussion paper series   2001 ( 1 )   1 - 25   2001.2

     More details

    Language:English  

    researchmap

  • Higher order normalizing transformations of asymptotic U-statistics for removing bias, skewness and kurtosis (vol 83, pg 47, 2000)

    Y Fujioka, Y Maesono

    JOURNAL OF STATISTICAL PLANNING AND INFERENCE   87 ( 2 )   365 - 366   2000.6

     More details

    Language:English   Publisher:ELSEVIER SCIENCE BV  

    Web of Science

    researchmap

  • U-統計量の正規近似の改良とその比較 Invited Reviewed

    Y. Fujioka, Y. Maesono

    経済学研究   66 ( 1 )   87 - 100   1999.10

     More details

    Language:Japanese  

    researchmap

  • Comparisons of variance estimators and their effects for studentized U-statistics

    MAESONO Y.

    The Australian National University Statistics Research Report No. SRR   40 - 95   1995

     More details

▼display all

Presentations

  • On the nonparametric quantile regression

    Shota Akiba, Yoshihiko Maesono

    Symposium on "Nonparametric Statistical Inference and Bayes Statistics"  2024.3 

     More details

    Event date: 2024.3    

    Language:Japanese   Presentation type:Oral presentation (general)  

    researchmap

  • カーネル型分位点推定量の漸近的性質について

    Yoshihiko Maesono, Takuya Shitara, Koudai Nakamura

    Institute of Mathematical Statistics Asia Pacific Rim Meeting  2024.1 

     More details

    Event date: 2024.1    

    Language:English   Presentation type:Oral presentation (general)  

    researchmap

  • On the nonparametric quantile regression

    Shota Akiba, Yoshihiko Maesono

    2023.12 

     More details

    Event date: 2023.12    

    Language:Japanese   Presentation type:Oral presentation (general)  

    researchmap

  • Asymptotic properties of kernel type quantile estimators

    Takuya Shitara, Yoshihiko Maesono

    Japanese Joint Statistical Meeting 2023  2023.9 

     More details

    Event date: 2023.9    

    Language:Japanese   Presentation type:Oral presentation (general)  

    researchmap

  • Asymptotic properties of kernel type quantile estimators

    Takuya Shitara, Yoshihiko Maesono

    Symposium on "Nonparametric Statistical Inference and Bayes Statistics"  2023.3 

     More details

    Event date: 2023.3    

    Language:Japanese   Presentation type:Oral presentation (general)  

    researchmap

  • Statistical Inference based on kernel type estimator

    Yoshihiko Maesono

    Symposium on "Frontier of Statistical Science"  2022.12 

     More details

    Event date: 2022.12    

    Language:Japanese   Presentation type:Oral presentation (general)  

    researchmap

  • Mean squared errors of kernel type quantile estimators

    Yoshihiko Maesono, Koudai Nakamura

    MSJ Autumn Meegint 2022  2022.9 

     More details

    Event date: 2022.9    

    Language:Japanese   Presentation type:Oral presentation (general)  

    researchmap

  • Improved confidence intervals for expectiles in risk management

    Yoshihiko Maesono, Spiridon Penev

    Japanese Joint Statistical Meeting 2022  2022.9 

     More details

    Event date: 2022.9    

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    researchmap

  • Improved confidence intervals for expectiles in risk management Invited

    Yoshihiko Maesono, Spiridon Penev

    5th International Conference on Econometrics and Statistics  2022.6 

     More details

    Event date: 2022.6    

    Language:English   Presentation type:Oral presentation (invited, special)  

    researchmap

  • Boundary-free kernel smoothed goodness of fit tests for data on general interval

    Rizky Reza Fauzi, Yoshihiko Maesono

    2022年度年会統計関連学会連合大会  ( Saitama University )   2022.3  日本数学会

     More details

    Language:Japanese   Presentation type:Oral presentation (general)  

    Properties of goodness-fit tests based on boundary-free kernel estimator of distribution functions.

    researchmap

  • Mean squared error of kernel type quantile estimator

    Kodai, Nakamura, Yoshihiko Maesono

    研究集会”第22回ノンパラメトリック統計解析とベイズ統計”  ( Bunkyo-ku, Tokyo )   2022.3  Masahiko

     More details

    Language:Japanese   Presentation type:Oral presentation (general)  

    We study asymptotic properties of the kernel quantile estimator.

    researchmap

  • Boundary-free kernel smoothed goodness of fit tests for data on general interval

    Rizky Reza Fauzi, Yoshihiko Maesono

    2020年度統計関連学会連合大会  ( On line )   2020.9  応用統計学会,日本計算機統計学会,計量生物学会,日本行動計量学会,日本統計学科,日本分類学会

     More details

    Language:Japanese   Presentation type:Oral presentation (general)  

    Properties of goodness-fit tests based on boundary-free kernel estimator of distribution functions.

    researchmap

  • Multivariate functional subspace classification for high-dimensional longitudinal data and its application International conference

    Fukuda Tatsuya, Misumi Toshihiro, Konishi Sadanori, Maesono Yoshihiko

    The 12th International Conference of the ERCIM WG on Computational and Methodological Statistics  ( Birbeck University of London )   2019.12  Computational and Methodological Statistics

     More details

    Language:English   Presentation type:Oral presentation (general)  

    researchmap

  • Automatic multivariate functional clustering for spatial longitudinal data International conference

    Arai Toshinori, Misumi Toshihiro, Matsui Hidetoshi, Konishi Sadanori, Maesono Yoshihiko

    The 12th International Conference of the ERCIM WG on Computational and Methodological Statistics  ( Birbeck University of London )   2019.12  Computational and Methodological Statistics

     More details

    Language:English   Presentation type:Oral presentation (general)  

    researchmap

  • Structural change detection via common principal component analysis International conference

    Matsukawa Tatsuya, Misumi Toshihiro, Konishi Sadanori, Maesono Yoshihiko

    The 12th International Conference of the ERCIM WG on Computational and Methodological Statistics  ( Birbeck University of London )   2019.12  Computational and Methodological Statistics

     More details

    Language:English   Presentation type:Oral presentation (general)  

    We propose a structural change detection method and discuss its applications to real data.

    researchmap

  • Automatic multivariate functional clustering for spatial longitudinal data

    Arai Toshinori, Misumi Toshihiro, Matsui Hidetoshi, Konishi Sadanori, Maesono Yoshihiko

    第24回 情報・統計科学シンポジウム  ( Kyushu University )   2019.12  統計科学研究会

     More details

    Language:Japanese   Presentation type:Oral presentation (general)  

    We propose a new classification method for spatial longitudinal data.

    researchmap

  • Subspace method for multivariate functional data and its application

    Fukuda Tatsuya, Misumi Toshihiro, Konishi Sadanori, Maesono Yoshihiko

    第24回 情報・統計科学シンポジウム  ( Kyushu University )   2019.12  統計科学研究会

     More details

    Language:Japanese   Presentation type:Oral presentation (general)  

    We propose a multivariate functional clustering method for spatial longitudinal data and discuss its application.

    researchmap

  • Structural change detection based on common principal component analysis and its application

    Matsukawa Tatsuya, Misumi Toshihiro, Konishi Sadanori, Maesono Yoshihiko

    第24回 情報・統計科学シンポジウム  ( Kyushu University )   2019.12  統計科学研究会

     More details

    Language:Japanese   Presentation type:Oral presentation (general)  

    We propose a structural change detection method and discuss its applications to real data.

    researchmap

  • 共変量を伴うデータに対するカーネル型ハザード関数推定

    Y. Maesono, M. Shimizu

    日本数学会総合分科会  ( 金沢大学 )   2019.9  日本数学会

     More details

    Language:Japanese   Presentation type:Oral presentation (general)  

    researchmap

  • Kernel-based Goodness-of-fit Test for Data with Boundaries

    Rizky Reza Fauzi, Y. Maesono

    統計関連学会連合大会  ( 滋賀大学 )   2019.9  統計関連学会連合

     More details

    Language:English   Presentation type:Oral presentation (general)  

    researchmap

▼display all

Awards

  • 日本統計学会小川賞

    1996.10   日本統計学会  

Research Projects

  • Improvement of nonparametric inference based on kernel type estimation and resampling method, and its application

    Grant number:22K11939  2022.4 - 2025.3

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (C)  Chuo University

      More details

    Grant amount: \4160000 ( Direct Cost: \3200000 、 Indirect Cost: \960000 )

    researchmap

  • A new type of volatility estimator defined by jump diffusion model

    Grant number:18K03431  2018.4 - 2023.3

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (C)  Tokyo City University

      More details

    Grant amount: \4290000 ( Direct Cost: \3300000 、 Indirect Cost: \990000 )

    researchmap

  • 多様なノンパラメトリック推測法の融合による新たな高精度統計手法の開発

    2016.4 - 2020.3

    日本学術振興会  科学研究費 

    前園 宜彦

      More details

    Authorship:Principal investigator  Grant type:Competitive

    researchmap

  • Statistical modeling of spatio-temporal data on natural and social phenomena, and those understanding

    Grant number:15H02670  2015.4 - 2019.3

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (B)  Kyushu University

    Nishii Ryuei, Koda Satoru

      More details

    Grant amount: \15730000 ( Direct Cost: \12100000 、 Indirect Cost: \3630000 )

    The following studies were conducted.
    1) In IGARSS 2015, a special session about the social application of the remote sensing imagery was orgenized with Columbia University. 2) Disturbance strom index was accurately predicted by regression model based on physical measurements about the solar activity. 3) Gene regulatory network was estated by sparse modeling of regression model on time-series of global gene expressions. 4) For super high-resolution land covering imagery, multi-label classification was proposed by machine learning by the use of hierarchical structure of the output layer and spatial dependency of the input layer.

    researchmap

  • ノンパラメトリック統計量の平滑化と高精度推測法の構築

    2015.4 - 2018.3

    日本学術振興会  挑戦的萌芽研究 

    Yoshihiko Maesono

      More details

    Grant type:Competitive

    Grant amount: \2860000 ( Direct Cost: \2200000 、 Indirect Cost: \660000 )

    researchmap

  • Asymptotic Expansions for U- and V-statistics with Degenerate Kernels

    Grant number:25400211  2013.4 - 2018.3

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (C)  Tokyo City University

    Kanagawa Shuya

      More details

    Grant amount: \5070000 ( Direct Cost: \3900000 、 Indirect Cost: \1170000 )

    We consider asymptotically normal statistics which are symmetric functions of N i.i.d. random variables. For these statistics we prove the va- lidity of an Edgeworth expansion with remainder of the large order of n to the power of (-2) under Cramer’s condition on the linear part of the statistic and moment assumptions for all parts of the statistic. By means of a counterexample we show that it is generally not possible to obtain an Edgeworth expansion with remainder of the large order of n to the power of (-2) without imposing additional assumptions on the structure of the nonlinear part of the statistic.

    researchmap

  • 高次有効性をもつスムーズなノンパラメトリック推測法の開発

    2012.4 - 2015.3

    日本学術振興会  挑戦的萌芽研究 

    Yoshihiko Maesono

      More details

    Grant type:Competitive

    Grant amount: \3120000 ( Direct Cost: \2400000 、 Indirect Cost: \720000 )

    researchmap

  • Statistical modeling of spatio-temporal data and quantitative grasp of phenomena

    Grant number:23300106  2011.4 - 2015.3

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (B)  Kyushu University

    NISHII Ryuei, NINOMIYA Yoshiyuki, MASUDA Hiroki, MAESONO Yoshihiko, TANAKA Shojiro, SHIMIZU Kunio, QIN Pan, KONISHI Sadanori, SAKATA Toshio

      More details

    Grant amount: \11570000 ( Direct Cost: \8900000 、 Indirect Cost: \2670000 )

    The aim of our research was to promote statistical modeling for spatio-temporal data acquired by actual phenomena, and grasp its characteristics through the modeling. Also we studied statistical properties of the models. The concrete results are as follows.
    1) We considered deforestation models where forest-covering-ratio is regressed by human population density and relief energy with spatial and temporal dependency. 2) Auto-regressive models with exogenous variables are extended through generalized linear models, and applied to actual data. Then, magnetic storm time index is accurately predicted by using physical measurements of solar activities. 3) Frequencies of weak earthquakes were shown to be affected by the solar wind. 4) Asymptotic theory for the parameter estimation of time series models described by stochastic differential equations was developed.

    researchmap

  • Nonlinear modeling based on high-dimensional data

    Grant number:21300106  2009.4 - 2014.3

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (B) 

    KONISHI Sadanori, NISHI Ryuei, MAESONO Yoshihiko, NINOMIYA Yoshiyuki, MASUDA Hiroki

      More details

    Grant amount: \16250000 ( Direct Cost: \12500000 、 Indirect Cost: \3750000 )

    The development of electronic measurement and instrumentation technologies enables us to accumulate a huge amount of data with complex structure and/or high-dimensional data. Through this research project we have investigated the problem of analyzing such datasets, and proposed various statistical modeling strategies including nonlinear regression modeling via L1 regularization, model evaluation and selection criteria, and Bayesian statistical modeling. Various regularization methods with L1 norm penalty have been investigated both in theoretical and numerical aspects. The problem of evaluating statistical models is a crucial issue in model building process. We proposed various types of model evaluation and selection criteria from both an information-theoretic point of view and a Bayesian approach. The proposed techniques may be used in the extraction of useful information and patterns from data with complex structure in the life sciences, systems engineering, and other fields.

    researchmap

  • 高度な情報抽出のためのノンパラメトリック推測理論の導出とその応用

    2009.4 - 2014.3

    日本学術振興会  基盤研究(B) 

    Yoshihiko Maesono, R. Nishii, S. Konishi, M. Sagae, Y. Fujii

      More details

    Grant type:Competitive

    Grant amount: \14560000 ( Direct Cost: \11200000 、 Indirect Cost: \3360000 )

    researchmap

  • Derivation of the nonparametric inference properties and its applicaiton

    2009.4 - 2014.3

    Japan Society for the promotion of Science  Grant-in-Aid for Scientific Research 

    MAESONO Yoshihiko

      More details

    Authorship:Principal investigator  Grant type:Competitive

    researchmap

  • 統計的リサンプリング法と高次漸近理論の融合による実用的な高精度推測法の開発

    2009.4 - 2012.3

    日本学術振興会  挑戦的萌芽研究 

    Yoshihiko Maesono

      More details

    Grant type:Competitive

    Grant amount: \2740000 ( Direct Cost: \2500000 、 Indirect Cost: \240000 )

    researchmap

  • 複雑な統計モデルでのノンパラメトリック推測法の改良とその応用の研究

    2004.4 - 2008.3

    日本学術振興会  基盤研究(B) 

    Yoshihiko Maesono, S. Iwamoto, S. Konishi, T. Nakai, H. Hyakutake, M. Uchida

      More details

    Grant type:Competitive

    Grant amount: \10990000 ( Direct Cost: \10300000 、 Indirect Cost: \690000 )

    researchmap

  • Studies on optimal values of sequential decision problems regarding to estimations

    Grant number:19510150  2007 - 2008

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (C) 

    NAKAI Toru, IWAMOTO Seiichi, TOKINAGA Shozo, MESONO Yoshihiko, MATSUMOTO Koichi

      More details

    Grant amount: \4550000 ( Direct Cost: \3500000 、 Indirect Cost: \1050000 )

    researchmap

  • Nonlinear multivariate analysis based on high-dimensional data and its application

    Grant number:17300089  2005 - 2008

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (B)  Kyushu University

    KONISHI Sadanori, NISHII Ryuei, MAESONO Yoshihiko, HYAKUTAKE Hiroto, NINOMIYA Yoshiyuki, MASUDA Hiroki, UCHIDA Masayuki

      More details

    Grant amount: \14870000 ( Direct Cost: \12800000 、 Indirect Cost: \2070000 )

    researchmap

  • 非決定性動的計画法の研究とその制御差分方程式への応用

    Grant number:15654019  2003 - 2005

    日本学術振興会  科学研究費助成事業  萌芽研究  九州大学

    岩本 誠一, 川崎 英文, 時永 祥三, 前園 宜彦, 藤田 敏治, 植野 貴之

      More details

    Grant amount: \3400000 ( Direct Cost: \3400000 )

    本平成17年度は全3年計画の最終年度に当たり、本研究のまとめと総括の年度である。本研究では確定的・確率的動的計画法(deterministic and stochastic dynamic programming)にとって代わり得る新たな動的計画法として非決定性動的計画法(non-deterministic dynamic programming)を導入しようとしている。
    この目的は概ね達成され、非決定性動的計画法の位置づけが明らかになり、さらに確定的動的計画法および確率的動的計画法に見られない新しい動的最適化問題群が明瞭に浮き彫りにされた。具体的にはコンピュータサイエンス分野での人工知能の設計において極めてよく用いられていることが判明した。また、離散的な数理パズルや数学的なゲームにおいてもいくつか興味ある問題が非決定性動的計画法で解かれることも分かった。その他に、確率論とその応用でよく用いられている停止時刻(stopping time)の概念を離散グラフや木の上に導入して、具体的な動的最適化問題に対して非決定性動的計画法で最適時刻(パターン)を構成した。これは数理ファイナンスにおけるアメリカンオプションをはじめとする満期日変動型オプションの再帰的価格付けを可能にした。この過程で有限段の最適停止問題において停止規則の総数の列挙も再帰的に示せ、その全体をグラフなどで具体的に分かり易く表示した。これにより、ややもするすると陥りがちな解の存在などの数学的な議論から抜け出して、最適停止問題の広域化、簡便化、親しみやすさへと繋がって行った。この研究によって停止時刻、情報集合など確率論特有の概念が非決定性システム上で構築でき、確率(probability)に替わって広く加重(weight)を用いた最適化が可能になった.また、いわゆる差分方程式の概念に最大化演算をもちいて複数個の差分方程式を制御するシステムを導入した。これによって制御差分方程式が具体的な形で表され、最適化を含まない(評価型)動的計画法によって解かれることが判明した。
    非決定性動的計画法と制御差分方程式に関するこれらの成果は国内は勿論、2003年EURO/INFORMS、ISMP18,2004年KES, ICOTA6,IWIF1および2005年IFORS17などの国際会議で発表し、日本発のオリジナルな研究であることが認知されるようになった。

    researchmap

  • 金融工学へのリサンプリング法の応用

    2002 - 2005

      More details

    Grant type:Competitive

    researchmap

  • Application of Resampling Method to Financial Engineering

    2001 - 2005

      More details

    Grant type:Competitive

    researchmap

  • Non-Additive Criterion on Controlled Markov Chains and its Applications to Mathematical Finance

    Grant number:13440036  2001 - 2004

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (B)  Kyushu University

    IWAMOTO Seiichi, TOKINAGA Syozo, NAKAI Toru, YASUDA Masami, KAWASAKI Hidefumi, FUJITA Toshiharu

      More details

    Grant amount: \9000000 ( Direct Cost: \9000000 )

    This project studies from a viewpoint of non-additivity, which is well-known as non-linearity in criterion. Our aim is to clarify an optimal structure both in policy and in system dynamics under the expected utility criteria. Further we also apply the results we have obtained for optimization scheme to non-optimization problems such as option evaluation in mathematical finance.
    It has been well known that dynamic optimizations such as in Markov decision processes have treated additive (linear) criteria e.g. discounted total expected reward. These optimizations are relatively easily performed because of linearity in expectation operator: However what will happen when we optimize such non-additive criteria? Our study begins with abandoning the linearity in expectation. Instead, we focus our attention to (a)monotonicity in expectation operator, (b)associativity in reward criteria and (c)successive applicability of state dynamics.
    By using these three properties, we have succeeded in establishing a large variety of optimization methods and in recognizing that these dynamic methods turn out to be fruitful in implemnentation/calculation. To be more concretely specific, we have obtained the following four results.
    (1)To have introduced policy classes and classified them into Markov, general, primitive and expanded Markov,
    (2)To have introduced two criterion classes and classified both into simple criterion (additive, multiplicative, maximum and terminal) and compound criterion (range, variance, ratio, sum excluding extrema and mid-range),
    (3)To have associated the policy classes with the two criterion classes and presented how to imbed the original problem into an expanded class of problems,
    (4)To have applied the results obtained for wide class of optimization problems in (1)-(3) to a class of non-optimization problems in mathematical finance such as option pricing.
    Throughout this study, we have clarified that a large class of optimization methods have been useful for a wide variety of criteria. These methods have been restricted to a small class of deterministic problems. Now our approach has shown that these methods are applicable to a huge class of optimization and non-optimization problems in stochastic, fuzzy or non-deterministic problems. In particular we have developed an evaluation method of a large class of options (derivatives) in mathematical finance. This is called dynamic pricing or recursive evaluation. Further more we have succeeded in developing some new derivatives such as options with random expiration date…Pacific options, look back American options and others.
    As a summary we have made dynamic optimization method fiuitful Thus dynamic programming, recursive method, and invariant imbedding turn out to be useful for a wide class of optimization and/or evaluation problems which inherits (i)non-additivity, (ii)non-linearity or (iii)non-determinancy. This project has just opened the door to overcome the three difficulties.

    researchmap

  • Mathematical modeling for high-dimensional nonlinear data and its application to the analysis of complex phenomena

    Grant number:13440034  2001 - 2004

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (B)  KYUSHU UNIVERSITY

    KONISHI Sadanori, HYAKUTAKE Hiroto, UCHIDA Masayuki, MAESONO Yoshihiko, YANAGAWA Takashi

      More details

    Grant amount: \11700000 ( Direct Cost: \11700000 )

    In recent years the wide availability of fast and inexpensive computers enables us to accumulate a huge amount of data, and the effective use of databases are required in order to create innovation and values and to solve important science and engineering problems. Statistical challenges posed by large data sets arise in such areas as genome databases in life science, remote-sensing data from earth observing satellites, POS data in marketing and economic data. Through this research project we have investigated the problem of constructing various types of statistical nonlinear modeling strategies and obtained the results in the following :
    (1)We proposed nonlinear modeling techniques ; determining a set of basis functions, estimating the unknown parameters by regularization and then evaluating the constructed model to select a suitable one among competing models. We describe modeling based on functional approach and introduce a generalized information criterion. Bayesian information criterion BIC is also extended in such a way that it can be applied to the evaluation of models estimated by the method of regularization.
    (2)We proposed functional regression modeling and functional discriminant analysis, using Gaussian radial basis functions along with the technique of regularization. The proposed method was applied to the analysis of yeast cell cycle gene expression data.
    (3)Approximate selection of embedding dimension and delay time have been a central issue of chaotic dynamical systems. We introduced the delay time and consider the estimation of embedding dimension and delay time.
    (4)Model selection criteria were presented for stochastic process from an information-theoretic approach. We derived asymptotic expansions for the distributions of statistics related to small diffusions and applied it to option pricing in economics.

    researchmap

  • リサンプリング法の有効利用と新しい応用の研究

    1999.4 - 2002.3

    日本学術振興会  基盤研究(B) 

    Yoshihiko Maesono, S. Konishi, S. Iwamoto, T. Yanagawa, T. Nakai

      More details

    Grant type:Competitive

    Grant amount: \6600000 ( Direct Cost: \6600000 )

    researchmap

  • 多期間ポートフォリオにおける評価系および最適政策の動的計画法による研究

    Grant number:13878077  2001 - 2002

    日本学術振興会  科学研究費助成事業  萌芽研究  九州大学

    岩本 誠一, 前園 宜彦, 中井 達, 時永 祥三, 植野 貴之, 藤田 敏治

      More details

    Grant amount: \2100000 ( Direct Cost: \2100000 )

    いわゆるマルコビッツのポートフォリオ理論では平均・分散基準の確定的最適化を数理計画法によって行っている。これは時間を含んだダイナミックな問題を、期待値操作または極限操作により、瞬時の静的問題として解析している。すなわち、時間推移に伴うダイナミズムの取り扱いを無視していた。しかし、本研究においては、【動的な問題には動的な解析】を通して、最適化を行っている。
    まず、数理ファイナンス分野おける新しい評価基準として単一評価クラスと複合評価クラスを導入して、その不確実性の下での動的最適化手法を提案している。とくに、リスクとリターンをマルコフ連鎖として確率変数列そのものとして取り扱い、制御マルコフ連鎖上で分数型基準の条件つき期待値を再帰的に最適化している。分数型評価は複合評価の典型的な基準の一つであるが、他に、範囲、分散などの複合型基準の動的最適化を行った。さらに、動的計画法を中心とした動学的最適化手法として、(1)原始政策法、(2)拡大マルコフ政策法、(3)(4)多段確率決定樹表を開拓し、既存の最適化手法では解けない問題を提案し、これらの最適解を導いた。また、動的最適化手法をより分かりやすく、説得力あるものにするために、各種グラフィックス表示およびその開発をおこなった。とくに、不確実性の下において非加法型評価の多段階意思決定過程の最適化を動的計画法によって行った。
    さらに加法型評価と非加法型評価との相違を最適解・アプローチにおいて解明し、三つの手法で多段決定過程の最適化を行った。ここでは評価系を加法・非加法の枠を超えて、広く単一・複合としてとらえ、動的計画法が広く適用できることを実例とともに示した。
    本研究によって、多期間ポートフォリオ理論に新しい評価基準が導入され、その下での互いに同等な動的最適化手法が広く利用できるようになった。これはまさしく本萌芽的研究の一つの成果である。

    researchmap

  • リサンプリング法の理論研究

    1999 - 2001

      More details

    Grant type:Competitive

    researchmap

  • Theoretical Study of Resampling Method

    1999 - 2001

      More details

    Grant type:Competitive

    researchmap

  • 条件付き期待値によるダイナミック・ポートフォリオ理論の構成とその応用

    Grant number:11874023  1999 - 2000

    日本学術振興会  科学研究費助成事業  萌芽的研究  九州大学

    岩本 誠一, 前園 宜彦, 中井 達, 時永 祥三, 藤田 敏治

      More details

    Grant amount: \2300000 ( Direct Cost: \2300000 )

    従来のポートフォリオ理論では平均・分散基準の確定的最適化を数理計画法によっておこなっているが、本研究においては、数理ファイナンス分野おける新しい評価基準として単一評価クラスと複合評価クラスを導入して、その不確実性の下での動的最適化手法を提案している。とくに、リスクとリターンを確率変数そのものとして取り扱い、制御マルコフ連鎖上で分数型基準の条件つき期待値を再帰的に最適化している。分数型評価は複合評価の典型的な基準の一つであるが、他に、比型、分散などの複合型基準の動的最適化をおこなっている。さらに、動的計画法を中心とした動学的最適化手法として、(1)全履歴法、(2)パラメトリック法、(3)マルコフ法、(4)多段確率決定樹表を開拓し、既存の最適化手法では解けない問題を提案し、これらの最適解を導いた。また、動的最適化手法をより分かりやすく、説得力あるものにするために、各種グラフィックス表示およびその開発をおこなった。とくに、不確実性の下において非加法型評価の多段階意思決定過程の最適化を動的計画法によって行った。具体的には、(1)事前条件付き意思決定過程と(2)事後条件付き意思決定過程の二つを新たに導入し、(3)条件なし(本来の)意思決定過程との最適解の構造およびそのアプローチにおいて三つの過程の相違点を明らかにした。
    本研究によって、閾値確率制御問題が上述の多様な方法で解けることが明らかになった。とくに、閾値確率最大化問題の逆問題は数理ファイナンスにおけるバリュー・アト・リスクの最小化問題なることがっわかり、バリュー・アト・リスクの最小化に新たに動的計画法・埋め込み法が適用できることになった。この二つの方法はこれまで確定的システムの最適化に多用されて成果を上げてきたが、本研究によって確率システム・あいまいシステムに対しても動的計画法・埋め込み法が適用できることが判明した。したがって、本来不確実性の下で変動するポートフォリオシステムの最適化方法が多様・多彩になってきた。これらはまさしく本萌芽的研究の成果である。

    researchmap

  • NONLINEAR STATISTICAL MODELING AND MODEL EVALUATION

    Grant number:09440082  1997 - 2000

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (B).  KYUSHU UNIVERSITY

    KONISHI Sadanori, TABATA Masahisa, NAKAO Mitsuhiro,t., YANAGAWA Takashi, MAESONO Yoshihiko, FUKUMOTO Yasuhide

      More details

    Grant amount: \10800000 ( Direct Cost: \10800000 )

    Modeling and model evaluation are crucial issues in scientific data analysis. Models are used for understanding the structure of system or process and for making trustworthy predictions in various fields of natural and social sciences. The data contain the information about the system under consideration and the objective of statistical analysis is to express this information in an understandable form using a statistical model. We also make inferences about the unknown aspects of random phenomena and seek an understanding of causal relationships. Now the wide availability of fast and inexpensive computers enables us to construct various types of nonlinear models for analyzing data with complex structure. Through this research project we have investigated the problem of constructing various types of nonlinear models and obtained the results in the following : (1) Model evaluation and selection criteria ; information-theoretic criterion which enables us to evaluate various types of nonlinear statistical models. (2) Nonlinear modeling based on kernel, spline, neural network. (3) Defining the embedding dimension and delay time in the chaotic time series with additive dynamic noise. (4) The estimation of the Lyapunov exponent for the nonlinear autoregressive time series models. (5) Techniques for the numerical vertification of solutions of differential equations. (6) A method to estimate the guaranteed error bounds of the finite element solutions for the Stokes problem. (7) Mathematical model of the earth's mantle movement. (8) A finite element analysis for a thermal convection problem with the infinite Parandl number on the earth's mantle convection. (9) The motion and expansion of a viscous vortex ring ; various dynamical aspects, such as formation, traveling speed, waves, instability, interactions. (10) The motion of an axisymmetric vortex ring of small cross-section in a viscous in compressible fluid. (11) Theory for normalizing transformations of asymptotic U-statistics. (12) The use of Weighted bootstrap methods.

    researchmap

  • Many-Sided study of Selberg type integrals

    Grant number:09440064  1997 - 1998

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (B)  KYUSHU UNIVERSITY

    KANEKO Jyoichi, KAZAMA Hideaki

      More details

    Grant amount: \5500000 ( Direct Cost: \5500000 )

    In our research, we mainly studied the twisted (co-)homology groups and the holonomic systems attached to the (deformed) Selberg type integrals. We regard the integral as the dual pairing of the twisted homology group and the twisted cohomology group, and so the fundamental problem is to construct the bases of these (co-)homology groups. We explicitly constructed the bases of the (co-)homology groups, and noticed that these bases are nothing but the ones obtained from the beta-nbc bases due to Falk and Terao. We also calculated the Gauss-Manin system explicitly in graph-theoretical terms (Duke Math. J.). Our de-formed Selberg type integral is also an example of A-type hypergeometric functions due to Gelfand-Kapranov-Zelevinsky. We have been investigating the so-called A-hypergeometric ideal describing the holonomic system of the integral, especially on its Cohen-Macaulay property and construction of the basis.
    The conjecture of Forrester predicts that the value of certain generalization of the original Selberg integral is also given by an explicit GAMMA product. We verified this in some cases by using the integration formula of Jack polynomials (Contemporary Math., to appear). We have been currently, working on this conjecture by employing Dunkl operators.
    Kazama (with S.Takayama) solved in the negative the long-standing conjecture of S.Nakano concerning **-problem on weakly 1-complete manifolds (Nagoya Math. J., to appear). They also investigated related problems on complex Lie groups (Nagoya Math. 3., to appear).

    researchmap

  • Development of index theory for C-algebras

    Grant number:08454032  1996    

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (B)  KYUSHU UNIVERSITY

    WATATANI Yasuo, MAESONO Yoshihiko, ISHIKAWA Nobuhiro, KAZAMA Hideaki

      More details

    Grant amount: \3100000 ( Direct Cost: \3100000 )

    Let M be a type II_1-factor and N a subfactor of M.V.Jones introduced Jones index [M : N] as a certain rank of M as N-module using the coupling constant. Kosaki and Longo extended Jones index theory for type III subfactors. The head investigator had extended Jones index theory for simple C^<**>-lgebras.
    In this research we introduced the notion of Hilbert C^<**>-bimodule by replacing the associativity condition in Rieffel's imprimitivity bimodules by the Pimsner-Popa type ineqality. The index of Hilbert C^<**>-bimodules measures the failure from imprimitivity bimodules. We also studied actions of countable discrete groups on Hilbert C^<**>-bimodules from the motivation of equivariant Morita equivalence for C^<**>-algebras and orbifold construction for subfactors. We considered crossed products of Hilbert C^<**>-bimodules and showed that a certain kind of free and ergodic action guarantees the irreducibility of the crossed product. We also have Takesaki-Takai duality for Hilbert C^<**>-bimodules. We gave a concrete example of the duality of Dynkin diagrams of type A and type D in the level of bimoules. We investigated a fusion rule of irreducible decomposition of iterative tensor products of a Hilbert C^<**>-bimodule and its conjugate.

    researchmap

  • 無限次元確率解析と微分幾何学

    Grant number:07640317  1995    

    日本学術振興会  科学研究費助成事業  一般研究(C)  九州大学

    杉田 洋, 前田 英敏, 前園 宣彦, 岩瀬 則夫, 山口 忠志, 風間 英明

      More details

    Grant amount: \2300000 ( Direct Cost: \2300000 )

    無限次元正則関数について本研究の代表者は以下のような知見を得たので報告する。
    無限次元正則関数の定義は使用目的によって様々なものが考えられるが、我々が採用した定義は確率解析に根ざしているShigekawaの定義である。これは複素Wiener空間上の加測関数(Wiener汎関数という)のうち正則な多項式関数(これは実質的に有限次元の正則関数である)のL_p-極限として得られるものである。さて、正則多項式自体は連続関数であるが極限として得られる正則Wiener汎関数は一般に連続ではない。しかし、正則性という強力な構造によって次のような無限次元Brown運動に対する細連続性を持つ。:正則Wiener汎関数は確率0の修正をすれば複素Wiener空間上の原点から出発する無限次元Brown運動の軌道に沿って時間1までは確率1で連続である。(H. Sugita, J. Math. Kyoto Univ., 34-4(1994)849-857.)
    この結果を踏まえて時間1以降の無限次元Brown運動と正則Wiener汎関数の関連を調べた。新しい知見は次の通り。:正則Wiener汎関数の上に述べた修正は「正則除外集合」という零集合上で行われ、無限次元Brown運動は時刻1までは確率1でそれに到達しない。しかし、時刻1を越えると到達する事があり得ることが分かった。このことは正則Wiener汎関数によっては時刻1を越える無限次元Brown運動の軌道に関して連続になり得ないことを示している。このようなことは有限次元では決して起こらないことで無限次元の特徴を示している。
    以上のような知見も含め最近の正則Wiener汎関数に関する研究について総合報告を作成した。それはProceedings of Taniguchi Symposium '94に掲載予定である。

    researchmap

  • ノンパラメトリック推測の漸近理論

    1984 - 1994

      More details

    Grant type:Competitive

    researchmap

  • Asymptotic Theory of Nonparametric Inference

    1984 - 1994

      More details

    Grant type:Competitive

    researchmap

  • nef接束をもつFano多様体の研究

    Grant number:05640049  1993    

    日本学術振興会  科学研究費助成事業  一般研究(C)  九州大学

    佐藤 栄一, 岩瀬 則夫, 児玉 哲夫, 前園 宜彦, 金子 譲一, 山口 忠志

      More details

    Grant amount: \2100000 ( Direct Cost: \2100000 )

    今年度の研究の主な成果は次の通りである。(研究代表者による)
    【.encircled1.】.〓Txがアンプルベクトル束を持つ非特異射影多様体は、“任意標数"の下で射影空間又は二次超曲面である。
    【.encircled2.】.Xを射影空間内のn次元非特異部分多様体とする。Xがその各点で〓(=m)次元の射影部分空間Pを含むと仮定する。その時,Xは非特異射影多様体上P^a束(a〓m)又はn=2mでかつ二次超曲面・グラスマン多様体Gr(m+1,)のいずれかである。但しPは最初の場合はファイバーに含まれ,後2つの場合はそれらが持つ最大次元(=m)の線型空間である。尚Gr(m+1,1)はp^<m+1>内の直線全体からなる多様体である。
    上の成果の特徴は1の場合 最小次数の有理曲線のありうべき特異点のタイプは“標数0"では扱い易いが“任意標数"の下では特異な状況が出現する。一方付加条件(〓Txから出てくる)により、その特異性について分析が可能になり,期待される結果が得られる。次に【.encircled2.】の場合を述べる。X内の“generic"なPについて,その法束Np/xの形は完全に決定できる。問題となるのは、PのX内の任意の変位P′の法束Np′/xがNp/xと同様の構造をもつことを示すことを示すことにある。それにはベクトル束の変形について詳細に調べることにより、可能になる。さらに最後のグラスマン多様体の場合は代数曲線のトレリの定理が本質的に関与している。
    他に研究分担者によるものとして
    【.encircled3.】(前園)U-統計量と関連するU-及びL-統計量についての正規近似の下限の考察
    【.encircled4.】(金子)ジャク多項式と青本の結果を使い多変数超幾何関数の新しいクラスの導入 等がある

    researchmap

  • 多次元U-統計量及び関連する統計量の漸近分布

    1991.4 - 1992.3

    文部省  奨励研究(A) 

    Yoshihiko Maesono

      More details

    Grant type:Competitive

    Grant amount: \900000 ( Direct Cost: \900000 )

    researchmap

  • Symmetric統計量の正規近似の精密化

    1987.4 - 1988.3

    文部省  奨励研究(A) 

    Yoshihiko Maesono

      More details

    Grant type:Competitive

    Grant amount: \1100000

    researchmap

  • U-統計量の分布の漸近展開

    1985.4 - 1986.3

    文部省  奨励研究(A) 

    Yoshihiko Maesono

      More details

    Grant type:Competitive

    Grant amount: \1000000 ( Direct Cost: \1000000 )

    researchmap

▼display all

Other

  • Editorial board member of Statistics

     More details

    学術誌Statistics 編集委員

    researchmap

Allotted class

  • 2024   Graduation Thesis Ⅰ   Department

  • 2024   Graduation Thesis Ⅱ   Department

  • 2024   Applied Mathematical Statistics 2   Department

  • 2024   Statistics 2   Department

  • 2024   Probability and Statistics   Department

  • 2024   Mathematical Statistics 1   Department

  • 2024   Mathematical Statistics 2   Department

  • 2024   Mathematical Statistics 3   Department

  • 2024   Advanced Seminar in Mathematics Ⅰ   Graduate school

  • 2024   Advanced Seminar in Mathematics Ⅱ   Graduate school

  • 2024   Doctoral Research Ⅰ   Graduate school

  • 2024   Doctoral Research Ⅱ   Graduate school

  • 2024   Doctoral Research Ⅲ   Graduate school

  • 2024   Doctoral Research Ⅳ   Graduate school

  • 2024   Doctoral Research Ⅴ   Graduate school

  • 2024   Doctoral Research Ⅵ   Graduate school

  • 2024   Special lecture on mathematics   Graduate school

  • 2024   Master's Research Ⅰ   Graduate school

  • 2024   Master's Research Ⅲ   Graduate school

  • 2024   Master's Research Ⅱ   Graduate school

  • 2024   Master's Research Ⅳ   Graduate school

  • 2024   Statistics Ⅰ   Graduate school

  • 2024   Statistics Ⅱ   Graduate school

▼display all

Teaching Experience

  • 品質管理

    Institution:九州大学

  • 数理統計

    Institution:九州大学

  • 統計数学

    Institution:九州大学

  • Quality Control

    Institution:Kyushu University

  • Mathematical Statistics

    Institution:Kyushu University

Committee Memberships

  • 2010.4 - Now

    Bulletin Infromatics and Cybernetics   編集委員長  

  • 2006.5 - Now

    Statistics   編集委員  

  • 2006 - Now

    Journal of the Korean Statistical Society   編集委員  

  • 2005.10 - 2010.3

    日本規格協会福岡支部   標準化セミナー主任  

  • 2000 - 2002

    日本統計学会   評議員  

Social Activities

  • 日本規格協会主催「標準化セミナー」講師

    Role(s): Lecturer

    1990.10 - 2008.3

     More details

    Type:Certification seminar

    researchmap