研究者詳細

研究発表
分割表示 >>   全件表示

48 件中 1 - 48 件目

年度
Year
題目又はセッション名
Title or Name of Session
細目
Authorship
発表年月(日)
Date
発表学会等名称 Name, etc. of the conference at which the presentation is to be given, 主催者名称 Organizer, 掲載雑誌名等 Publishing Magazine,発行所 Publisher,巻/号 Vol./no.,頁数 Page nos.
2018  WeiSSVM model and its applications to cylindrical data  単独  2018/12 
11th International Conference of the ERCIM Working Group on Computational and Methodological Statistics  , Econometrics and Statistics   

概要(Abstract)  

備考(Remarks)  

2018  Recent cylindrical models and their application to tree data set  単独  2018/11 
融合する統計科学   

概要(Abstract)  

備考(Remarks)  

2018  多変量歪正規分布における単純なアルゴリズムによるパラメータ推定  単独  2018/09 
2018年度統計関連学会連合大会   

概要(Abstract)  

備考(Remarks)  

2018  Models for cylindrical data and their applications  単独  2018/06 
The 2nd International Conference on Econometrics and Statistics (EcoSta 2018)  , Econometrics and Statistics   

概要(Abstract) Recent cylindrical models are reviewed. The WeiSSVM model has numerous good properties, such as simple normalizing constant and hence very tractable density, parameter-parsimony and interpretability, maximum entropy characterization, good circular-linear dependence structure, easy random number generation thanks to known marginal/conditional distributions, and flexibility illustrated via excellent fitting abilities. We also review some other related models. As an illustrative example, some of the models are applied in analyses of cylindrical data set. 

備考(Remarks)  

2018  A cylindrical distribution whose linear part is heavy-tailed  共同  2018/06 
The 2nd International Conference on Econometrics and Statistics (EcoSta 2018)  , Econometrics and Statistics   

概要(Abstract) There exist many examples of heavy-tailed phenomena such as insurance losses and returns in financial data, heavy-precipitation data, and heavy burst of teletransmission and Internet activity. Potential applications are combinations of linear and circular data through 24-hours clock for example as the circular part. If the cylindrical distributions whose linear parts can model only light-tailedness are applied to such data, the estimation and test may be biased by linear large observations, and it leads to wrong results. We propose a cylindrical distribution heavy-tailed for the linear part through a generalized Gamma mixture of Abe-Ley distribution whose linear part is related to a Weibull distribution. The conditional distribution of the linear variable given circular variable is a generalized Pareto distribution and therefore, it might not have any conditional moments, but the mode and median are expressed by closed forms. As an illustrative example, we fit the proposed distribution with likelihood techniques to earthquake data, which consists of the turning angles for epicenters and magnitude during 72 hours before the 2011 Great East Japan Earthquake, and compare the result with those by other cylindrical distributions each of whose linear part model only light-tailedness. 

備考(Remarks)  

2017  A flexible cylindrical model as a combination of the Weibull and SSVM distributions for cylindrical data  単独  2017/6 
Advances in Directional Statistics (ADISTA17)   

概要(Abstract) We consider a cylindrical model obtained by combining the sine-skewed von Mises distribution with the Weibull distribution. Our proposed model, WeiSSVM model, has numerous good properties such as, simple normalizing constant and hence very tractable density, parameter-parsimony and interpretability, maximum entropy characterization, good circular-linear dependence structure, easy random number generation thanks to known marginal/conditional distributions, and flexibility illustrated via excellent fitting abilities. As an illustrative example, our model is applied in analyses of blue periwinkle data set.  

備考(Remarks)  

2017  Asymptotically optimal inference for two modal concentration of antipodally symmetric circular distributions  共同  2017/6 
The 1st International Conference on Econometrics and Statistics (EcoSta 2017)   

概要(Abstract) In this talk, the optimal asymptotic inference for antipodal symmetry, using a family of bimodal distributions on the circle, is considered when the center direction of symmetry is specified. To adapt the Le Cam theory, we consider the reparameterization of the existing cosine perturbed bimodal models on the circle.
The properties of the uniform local asymptotic normality (ULAN) for the cosine perturbed models are described.
Finally, as an illustrative example, our developed tests are applied to the movements of 76 female turtles.  

備考(Remarks)  

2017  Bayesian estimation for the inverse Batschelet distributions on the circle  共同  2017/6 
The 1st International Conference on Econometrics and Statistics (EcoSta 2017)   

概要(Abstract)  

備考(Remarks)  

2017  Circular time series and statistical inference  単独  2017/6 
The 1st International Conference on Econometrics and Statistics (EcoSta 2017)  , Toshihiro Abe   

概要(Abstract)  

備考(Remarks)  

2017  On transformation of scale distributions on the circle with mode and antimode preserving property  共同  2017/12 
10th International Conference of the ERCIM Working Group on Computational and Methodological Statistics  , Econometrics and Statistics  , 114   

概要(Abstract)  

備考(Remarks)  

2017  Pareto type probability distribution for cylindrical data  共同  2017/12 
10th International Conference of the ERCIM Working Group on Computational and Methodological Statistics  , Econometrics and Statistics  , 18   

概要(Abstract)  

備考(Remarks)  

2017  Bayesian inference for mode preserving distributions on the circle  共同  2017/12 
10th International Conference of the ERCIM Working Group on Computational and Methodological Statistics  , Econometrics and Statistics  , 170   

概要(Abstract)  

備考(Remarks)  

2017  On estimating finite mixtures of sine-skewed von Mises distributions  共同  2017/12 
10th International Conference of the ERCIM Working Group on Computational and Methodological Statistics  , Econometrics and Statistics  , 170   

概要(Abstract)  

備考(Remarks)  

2017  Circular models and their statistical inference  単独  2017/12 
10th International Conference of the ERCIM Working Group on Computational and Methodological Statistics  , Toshihiro Abe   

概要(Abstract)  

備考(Remarks)  

2017  On mode and antimode preserving circular distributions  共同  2017/11 
 

概要(Abstract)  

備考(Remarks)  

2017  On estimating finite mixtures of skew-rotationally-symmetric distributions  共同  2017/11 
 

概要(Abstract)  

備考(Remarks)  

2017  On estimating finite mixtures of sine-skewed circular distributions  共同  2017/10 
Waseda International Symposium -- Recent Developments for Statistical Asymptotic Theory for Time Series & Circular Distributions --   

概要(Abstract)  

備考(Remarks)  

2017  A mode and antimode preserving circular distribution and its properties  単独  2017/10 
Kyoto International Seminar   

概要(Abstract)  

備考(Remarks)  

2017  On a mode preserving circular distribution and its Bayesian inference  共同  2017/09 
2017年度統計関連学会連合大会   

概要(Abstract)  

備考(Remarks)  

2017  シリンダー上のPareto型分布  共同  2017/09 
2017年度統計関連学会連合大会   

概要(Abstract)  

備考(Remarks)  

2016  A simple cylindrical distribution and its applications  単独  2017/3/6 
High Dimensional Statistical Analysis for Time Spatial Processes & Quantile Analysis for Time Series  , Taniguchi Masanobu   

概要(Abstract)  

備考(Remarks)  

2016  Symmetric circular distributions and their sine-skewed extensions  単独  2017/3/3 
Statistical Analysis for High-Dimensional, Circular or Time Series Data  , Shiraishi Hiroshi   

概要(Abstract)  

備考(Remarks)  

2016  方向統計学における統計的分布とその推測  単独  2016/2/20 
OR中部支部   

概要(Abstract)  

備考(Remarks)  

2016  A simple cylindrical model as a combination of the Weibull and sine-skewed von Mises distributions  単独  2016/12/11 
9th International Conference of the ERCIM WG on Computational and Methodological Statistics  , CMStatistics 2016   

概要(Abstract) A cylindrical model is considered obtained by combining the sine-skewed von Mises distribution with the Weibull distribution. The WeiSSVM model has numerous good properties such as simple normalizing constant, and hence very tractable density, parameter-parsimony and interpretability, maximum entropy characterization, good circular-linear dependence structure, easy random number generation thanks to known marginal/conditional distributions, and flexibility illustrated via excellent fitting abilities. As an illustrative example, our model is applied in analyses of periwinkle data set. 

備考(Remarks)  

2016  Weibull分布とsine-skewed von Mises分布を用いたシリンダー上の分布の生成  単独  2016/11/8 
複雑な生命現象を読み解くための大規模データ解析とモデリング  , 植木優夫   

概要(Abstract)  

備考(Remarks)  

2015  Length dependent models for cylindrical data through sine skewed wrapped Cauchy distribution  単独  2015/12/14 
8th International Conference of the ERCIM WG on Computational and Methodological Statistics  , CMStatistics 2015   

概要(Abstract) There has been an increased interest towards to the cylindrical distributions in recent years. The combination of direction and length, such as a pair of wind direction and its strength, can be regarded as the cylindrical data. Although some cylindrical models are well known, there are a few cylindrical models compared with the circular models. In this talk, we propose another class of cylindrical distributions on a bounded domain that combine circular and Beta type distributions with certain dependence structure. The model has the simple normalizing constant. As a special case, we propose a cylindrical distribution that has a structure of the Kumaraswamy and sine-skewed wrapped Cauchy distributions. The advantages of such the selection are a general form of the trigonometric moments, simple generation of random number and explicit form of the mode. 

備考(Remarks)  

2015  A cylindrical model for wind direction and velocity  単独  2015/11/05 
Adolphe Quetelet Seminar Series  , Ghent University   

概要(Abstract) In this talk, I proposed length dependent cylindrical models for wind data. In many cases, the distribution of the wind direction around sea coast has two modes. For this purpose, I gave a review of some circular distributions generated by perturbation of the symmetric circular distributions. Then by combining the existing methods, cosine-perturbation and sine-skewing, I proposed a good fitting model for the wind direction. Then making use of the recently introduced method by Abe \& Ley, I introduced a new class of cylindrical models. The mathematical properties of the model was also investigated. As an illustrative example, I considered the parameter estimation of our model for the wind directions and speeds at Namie district.  

備考(Remarks)  

2015  シリンダー上の確率分布とその周辺  単独  2015/09/15 
日本数学会2015年度秋季総合分科会  , 日本数学会   

概要(Abstract) 本講演では, 前半では円周分布の発展について述べ, 後半ではこれらを基にしたシリンダー分布について報告した. まずはじめに, 線形の統計学と性質が異なる角度データに対する
平均方向と平均合成ベクトル長, 円周分布の確率密度関数を定義する. 次に, 既存の対称な円周分布, 近年研究が盛んになってきている非対称な円周分布, そして, 検定手法を紹介した. 後の比較のために, 既存のシリンダー上の分布も紹介し, ある性質を示すデータに対して, 単純で扱いやすいシリンダー上の分布を生成した.
また, blue periwinkleの(移動方向, 移動距離)のデータに対して, 提案分布をパラメータ推定した例も紹介した.  

備考(Remarks)  

2015  ベータ型の分布を用いたシリンダー分布  単独  2015/09/08 
2015年度統計関連学会連合大会   

概要(Abstract) (風向, 風力)の組のような角度と大きさの組のデータは
シリンダー上のデータとみなすことができる. このようなデータの例はBreckling (1989)等で見ることができる. 本報告では, 既存の円周分布と実軸上の分布を組み合わせ, 新しいシリンダー分布を提案した.  

備考(Remarks)  

2014  モード不変性を持つ逆Batschelet分布  単独  2015/03/14 
応用統計学会2015年度年会   

概要(Abstract)  

備考(Remarks)  

2014  A tractable, parsimonious and highly flexible model for cylindrical data  単独  2015/02/24 
ISM Symposium on Environmental Statistics 2015   

概要(Abstract)  

備考(Remarks)  

2014  Linear-circular models and their properties  単独  2014/12/07 
7th International Conference of the ERCIM WG on Computational and Methodological Statistics (ERCIM 2014)   

概要(Abstract)  

備考(Remarks)  

2014  長さと角度を変量に持つ分布族  単独  2014/10/25 
多様な分野における統計科学の教育・理論・応用の新展開   

概要(Abstract)  

備考(Remarks)  

2014  既知の方向周りでの対蹠対称性に関する漸近最適推測論  共同  2014/09/14 
2014年度統計関連学会連合大会   

概要(Abstract)  

備考(Remarks)  

2014  円柱上の確率分布とその森林樹木の樹冠形状データへの応用  共同  2014/08/27 
方向データの統計モデリングと応用事例   

概要(Abstract)  

備考(Remarks)  

2014  軸対称確率分布について  未設定  2014/08/27 
方向データの統計モデリングと応用事例   

概要(Abstract)  

備考(Remarks)  

2014  A multivariate extension of the skew-unimodal distributions with mode-preserving property  単独  2014/08/07 
2014 Joint Statistical Meetings (JSM 2014)   

概要(Abstract)  

備考(Remarks)  

2014  Skew-symmetric circular distributions generated by sine perturbation  単独  2014/06/30 
Institute of Mathematical Statistics Asia Pacific Rim Meeting (IMS-APRM 2014)   

概要(Abstract)  

備考(Remarks)  

2014  Univariate skew-unimodal distributions with mode-preserving property  単独  2014/06/14 
3rd Stochastic Modeling Techniques and Data Analysis International Conference (SMTDA2014)   

概要(Abstract)  

備考(Remarks)  

2014  Skewed circular distributions with unimodality and mode-preserving property  単独  2014/05/21 
Advances in Directional Statistics   

概要(Abstract)  

備考(Remarks)  

2013  Skew-symmetric distributions on the circle with unimodality and mode-preserving property  単独  2014/01/14 
Advances and Applications in Distribution Theory   

概要(Abstract)  

備考(Remarks)  

2013  A classification method for absorption spectrum of considering proximity peak in NMR  共同  2013/11/14 
ISPACS 2013   

概要(Abstract)  

備考(Remarks)  

2013  Symmetric circular distributions and their sine perturbations  単独  2013/10/21 
Workshop on Stein's method and related topics   

概要(Abstract)  

備考(Remarks)  

2013  Skew distributions with unimodality and mode-preserving property  単独  2013/10/18 
seminar at the Université Libre de Bruxelles   

概要(Abstract)  

備考(Remarks)  

2013  モード不変性をもつ円周上の非対称分布族  単独  2013/09/10 
2013年度統計関連学会連合大会   

概要(Abstract)  

備考(Remarks)  

2013  A new family of unimodal skew-symmetric distributions with mode-invariance  共同  2013/08/07 
2013 Joint Statistical Meetings   

概要(Abstract)  

備考(Remarks)  

2013  A family of unimodal skew-symmetric distributions on the circle  単独  2013/08/03 
15th IMS New Researchers Conference   

概要(Abstract)  

備考(Remarks)  

2013  Skew circular models through sine perturbation  単独  2013/06/29 
Seminar on Time Series and Financial Engineering   

概要(Abstract)  

備考(Remarks)  

Page: [<<PREV] [1] [NEXT>>]