早稲田大学理工学研究所研究重点研究「統計科学と金融工学」セミナー
(
Project Research Seminar on Statistical Science & Financial Engineering by Kiban(A)(15H02061), Research Institute for Science & Engineering, ＆ 早稲田大学理工談話会))

new (2017/2/23)

Waseda International Symposium

Topic: Recent Developments in Time series Analysis: Quantile Regression, High Dimensional Data & Causality

Date: February 26 -28, 2018

Venue：Waseda University, Nishi-Waseda Campus, Building 63, 2nd Floor, Room 5
(Access map:https://www.waseda.jp/top/en/access/nishiwaseda-campus)

Organizer：Masanobu TANIGUCHI (Research Institute for Science & Engineering, Waseda University)

program⇒http://www.taniguchi.sci.waseda.ac.jp/2017_WASEDA_SP.pdf

Supported by:
(1) Kiban (A-15H02061) M. Taniguchi, Research Institute for Science & Engineering, Waseda University
(2) Tokutei-Kadai (B) M. Taniguchi, Research Institute for Science & Engineering, Waseda University

Date: August 1, 2017,    15:30 - 17:00

Location: Nishi-Waseda Campus, Building 63-1st Floor Meeting Room
(http://www.sci.waseda.ac.jp/access/)

Abstract.
This paper investigates the adequacy of the matrix exponential spatial specification (MESS) as an alternative to the widely used spatial autoregressive model (SAR). We first analyze the partial and marginal covariance structures, finding similar behavior for the MESS and SAR models in particular cases. We then propose a new implementation of Bayesian parameter estimation for the MESS model with vague prior distributions, which is shown to be precise and computationally efficient, and whose predictive accuracy is comparable to that of the SAR model. Our further proposal of a model including spatial splines among the regressors increases the predictive accuracy of the matrix exponential specification with regard to the modeling of the covariance matrix.

Date: June 23, 2017,  15:30 - 17:00

Location: Nishi-Waseda Campus, Building 63-1st Floor Meeting Room
(http://www.sci.waseda.ac.jp/access/)

Abstract.  This paper investigates the adequacy of the matrix exponential spatial specification (MESS) as an alternative to the widely used spatial autoregressive model (SAR). We first analyze the partial and marginal covariance structures, finding similar behavior for the MESS and SAR models in particular cases. We then propose a new implementation of Bayesian parameter estimation for the MESS model with vague prior distributions, which is shown to be precise and computationally efficient, and whose predictive accuracy is comparable to that of the SAR model. Our further proposal of a model including spatial splines among the regressors increases the predictive accuracy of the matrix exponential specification with regard to the modeling of the covariance matrix.

Title: Computable Bounding Functions for Expectation, Boundary Value and Obstacle Problems

Abstract: The computation of expectations involving stochastic processes has long been one of the central issues, in one form or another, in various fields of natural and social sciences, such as the Fokker-Planck equation, financial derivatives pricing, the assessment of ruin probabilities of an insurance company, to name just a few.
In this talk, we propose novel methods for obtaining hard bounding functions, without recourse to sample path simulation, without truncating the naturally unbounded domain that arises in this problem, and without discretizing the time and state variables. Unlike accurate approximate solutions via the existing discretization-based methods, our hard bounding functions are free from statistical error and act as pointwise 100% confidence intervals within which the unknown solution is guaranteed to exist. The proposed approaches can be applied to a variety of problem settings, such as mixed boundary conditions, stochastic volatility, stochastic processes with jumps, regime-switching and obstacle problems. Numerical results are presented throughout to support our theoretical developments and to illustrate the effectiveness of the proposed approaches.

This talk consist of two parts; (i) optimization and (ii) perturbation.
(i)
We propose a novel method for obtaining and tightening hard bounding functions for the expected value on stochastic differential equations with the help of the mathematical programming and the Dynkin formula.
In a single implementation of semi-definite programming, the proposed approach obtains explicit bounds in the form of piecewise polynomial functions, which bound the expectation over the whole domain both in time and state. As a consequence, these global bounds store a continuum of bounding information in the form of a finite number of polynomial coefficients.
In this talk, we pay particular attention to the American style option pricing problem.
(ii)
It is often the case that expectations are easy to compute for a simple model, while small perturbations make the computation of expectation suddenly prohibitive. We propose a novel method for measuring the impact of such small perturbations in expectations without significant computing effort. Our hard bounding functions are deterministic in the form of Markov-type inequalities, parametrized by the perturbation parameter, so that the upper and lower bounds converge to each other when the perturbation tends to vanish. The proposed method requires only well-developed numerical methods for boundary value problems for partial differential equations and elementary numerical integration of smooth functions.

＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝
10月のプロジェクトセミナーは下記との共催とさせていただきます

－－－－－－－－－－－－－－－－－－
(I) Waseda International Symposium

”High Dimensional Statistical Analysis for Time Spatial Processes, Quantile and Empirical Likelihood Analysis for Time Series”
Date: October 24 - 26, 2016
Venue: Waseda University Nishi-Waseda Campus Building 55S 2nd Floor, Room 3
(Access map: http://www.sci.waseda.ac.jp/en g/access/)
Organizer: Masanobu TANIGUCHI

プログラム：http://www.taniguchi.sci.wased a.ac.jp/WIS_ver3.pdf

－－－－－－－－－－－－－－－－－－－

＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝

(Research Seminar on Statistics and Financial Mathematics (supported by Kiban(A)))
および、早稲田大学理工学術院講演会共催
----------------------------------------------------------------------

Date: September 2 (Fri) 13:30 - 17:00

Location: Nishi-Waseda Campus, Building 63-1st Floor Meeting Room
(http://www.sci.waseda.ac.jp/access/)

(I) 13:30 - 15:00

Department of Management, Information and Production Engineering, University of Bergamo (Italy)

(II) 15:30 - 17:00

情報通信研究機構・未来ICT研究所, フロンティア創造総合研究室

＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝
----------------------------------------------------------------------------------
セミナーのお知らせ

(http://www.sci.waseda.ac.jp/access/)

(I) 15:00-16:00
講演題目：L1-自己加重経験尤度を用いた非正則・無限分散モデルの頑健な検定法の構成
講演者：明石　郁哉（早稲田大学応用数理学科）
Abstract：本公演では、経験尤度法を用いた検定方式を統一的に構成することを目的
とする。特に、モデルの計画行列に対する 正則性の仮定と、誤差項の有限分散性の仮

一般的な枠組みの構成を行う。具体的には、自己加重と分位点回帰の 手法を用いて

カイ二乗分布に収束し、 未知母数の推定を省略した検定を行うことが可能となる。さらに

random weighting bootstrap法に基づく検定統計量や 自己加重型Wald統計量と比較
し、経験尤度法の利点を明らかにする。

(II) 16:00-17:00
講演題目：Statistical theory for quantiles in frequency domain
講演者：劉　言（早稲田大学応用数理学科）
Abstract：In this talk, we discuss estimation and hypothesis testing for quantiles
in frequency domain of time series models. For second order stationary stochastic
processes, the spectral distribution function is uniquely determined by
the autocovariance functions of the processes. We focus on the sinusoidal models,
which are contained in the second order stationary processes. The sinusoidal
components, which show the nonlinear feature, correspond to jumps in the spectral
distribution function. We define the quantiles of the spectral distribution function and
propose quantile estimator in frequency domain as it in time domain. Although the
quantile estimator has consistency, it is not asymptotically normal, which is a peculiarity
compared with the estimator in time domain. We propose a modified quantile estimator
for asymptotic normality with tractability in hypothesis testing for sinusoid models.
We conclude our talk with several numerical results.

17:30- 懇親会（参加費無料）
場所：５６号館地下、生協食堂

----------------------------------------------------------------------------------

＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝

(Research Seminar on Statistics and Financial Mathematics (supported by Kiban(A)))

５月のセミナーは、下記、数学・応数談話会に合流しますので、お気軽にご参加ください。
-----------------------------------------------------------------------------

(http://www.sci.waseda.ac.jp/access/)

（株）データサイエンスコンソーシアム代表取締役

Abstract:

とづき具体例を用いながらわかりやすく解説する．
＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝

----------------------------------------------------------------------------------
セミナーのお知らせ

の両面から世界中で活発に研究されています．ゲノム科学・情報工学・金融

そうとしています．高次元データは，上手に扱わないとノイズしか聞こえて
きません．しかし，適切に扱えば，驚くほど豊富な情報を語ってくれるのです．
本講演は，3月19日に開催された日本数学会市民講演会での拙講演について，
リクエストに応える形で，再びお話をさせて頂くものです．高次元の統計学
には，従来の統計学の枠組みを超えた新しい発想が必要になることをご覧に

など，必ずしも専門家ではない方々にも最先端の雰囲気をお伝えできればと

----------------------------------------------------------------------------------
セミナーのお知ら せ

Date: January 27 (Wed), 2016, 14:40 - 16:10

Location: Nishi-Waseda Campus, Building 63-1st Floor Meeting Room

$Xt=B_t+G_t, t∈[0,T]$,
where $B_t$ is a Brownian motion and $G_t$ is an independent centered
Gaussian process. We obtain a new canonical innovation representation of X,
using linear filtering theory. When the kernel
$\frac{\partial^2}{\partial^2K(s,t)}= \partial s \partial t E G_sG_t,$
has a weak singularity on the diagonal, our results generalize the
classical innovation formulas beyond the square integrable setting. For
kernels with stronger singularity, our approach is applicable to
processes with additional “fractional” structure, including the mixed
fractional Brownian motion from mathematical finance. We show how
previously known measure equivalence relations and semimartingale
properties follow from our canonical representation in a unified way,
and complement them with new formulas for Radon-Nikodym densities. For
the application, we will use the asymptotic eigenvalues method to
estimation the drift parameter in the mixed fractional O-U process.
This work will be published from 'Annals of Probability' in the near
future.

----------------------------------------------------------------------------------
セミナーのお知ら せ

「金融数理および年金数理研究」セミナー
( Project Research Seminar on Financial and Pension Mathematics
(supported by Kiban(A)(15H02061), Research Institute for Science & Engineering, ＆　早稲田理工談話会) )

Date: December 22 (Tues), 2015, 15:30 ― 17:00

Location: Nishi-Waseda Campus, Building 63-1st Floor Meeting Room

Speaker：　Taiji Suzuki（Tokyo Institute of Technology）

Topic： Statistical properties of high dimensional low rank tensor estimators

Abstract: We investigate the statistical convergence rate of a Bayesian low-rank tensor estimator,
and derive the minimax optimalrate for learning a low-rank tensor. Our problem setting is the regression problem
where the regression coefficient forms a tensor structure. The convergence rate of the Bayes tensor estimator
is analyzed in terms of both in-sample and out-of-sample predictive accuracies. It is shown that
a fast learning rate is achieved without any strong convexity of the observation. Moreover, we show that
the method has adaptivity to the unknown rank of the true tensor. Finally, we show the minimax optimal learning rate
for the tensor estimation problem, and thus show that the derived bound of the Bayes estimator is tight
and actually near minimax optimal. If time permitted, we will also discuss the non-parametric estimation
of a tensor product of non-linear functions.

----------------------------------------------------------------------------------
セミナーのお知ら せ

「金融数理および年金数理研究」セミナー案内

(Project Research Seminar on Financial and Pension Mathematics
(supported by Kiban(A)(15H02061), Research Institute for Science & Engineering)
)

１０月と１１月の上記セミナーは、下記と共催で行いますので、ご参加よろしくお願いします。

Date: November 9 (Mon.) - 11 (Wed.), 2015

Location: Waseda University, Nishi-Waseda Campus, Building 55N 1st Floor Room 02A

プログラム＆アブストラクト（Program & abstract）：
http://www.taniguchi.sci.waseda.ac.jp/2015hokoku/WIS15_final.pdf

----------------------------------------------------------------------------------
セミナーのお知ら せ

「金融数理および年金数理研究」セミナー

(Project Research Seminar on Financial and Pension Mathematics
(supportedby Kiban(A)(15H02061), Research Institute for Science & Engineering & 早稲田理工談話会)
)

Date: August 31 (Mon), 2015,  15:00 — 17:30

Location: Nishi-Waseda Campus, Building 63-1st Floor Meeting Room

(1) 15:00 − 16:00

Speaker: Shu-Hui Yu, Institute of Statistics, National University of Kaohsiung
Topic I: Asymptotic inefficiency of BIC and asymptotic efficiency of TSIC: the case of an I(d) process

Abstract: We consider in this paper an I(d) autoregressive (AR) process, d>=0 is an unknown integer. While Sin and Yu (2015) show that Akaike's information criterion (AIC) is
asymptotically inefficient when the lag order is finite, this paper shows that when the lag order is infinite with (a) exponentially decaying AR coefficients, or (b) algebraically
decaying AR coefficients, Bayesian information criterion (BIC) is asymptotically inefficient. These results motivate us to combine the strengths of AIC and BIC, yielding a so-called
two-stage information criterion (TSIC) for a general I(d) AR process. We show that TSIC is asymptotically efficient in the aforementionedthree scenarios.
The paper concludes with a simulation study.

(2) 16:00 − 17:30

Speaker: Ching-Kang Ing, Institute of Statistical Science, Academia Sinica
Topic
II: Model Selection for High-Dimensional Time Series

Abstract: In the past decade, model selection for high-dimensional regression models is one of the most vibrant research topicsin statistics. However, most of the attention has been
devoted to situations where observations are independent, and hence time series data are precluded. Inthis talk, I shall address model selection problems for some high-dimensional
time series models, including high-dimensional stochastic regression models and high-dimensional regression models with correlated errors. I will present rates of convergence of
the orthogonal greedy algorithm (OGA) under various sparsity conditions. I will also show that when the high-dimensional information criterion (HDIC) of Ing and Lai (2011) is used in
conjunction with the OGA, the resultant predictor achieves the optimal error rate. Rates of convergence of the OGA are furtherestablished under model misspecification. Applications
of this latter result to model selection for high-dimensional interaction models will also be given.

----------------------------------------------------------------------------------

Date: June 24 (Wed), 2015 15:30 -- 17:00

Location: Nishi-Waseda Campus, Building 63-1st Floor Meeting Room

（１） 正規定常過程の自己共分散行列の縮小推定
須藤　慶大（早稲田大学　基幹理工学研究科）

（２） Discriminant and cluster analysis of high-dimensional time series data by a class of disparities
長幡　英明（早稲田大学基幹理工学研究科）＊,
劉　　言（早稲田大学基幹理工学研究科）,
内山　弘隆（早稲田大学基幹理工学研究科）,
谷口　正信（早稲田大学　理工学研究所）

----------------------------------------------------------------------------------

Date: May 27 (Wed), 2015 15:30 -- 17:00

Location: Nishi-Waseda Campus, Building 63-1st Floor Meeting Room

アブストラクト:
高次元データにおける高精度な判別法とPCAを用いたクラスタ−分析法を紹介する。

を導出することで最適性について議論する。さらに、その評価式にもとづき、冗長な

クラスター分析では、母集団に混合分布を考え、高次元小標本データの幾何学的表

です。

----------------------------------------------------------------------------------

Date: April 29 (Wed), 2015 15:30 - 17:00

Location: Nishi-Waseda Campus, Building 63-1st Floor Meeting Room

ア ブストラクト：In this talk I will discuss central limit and bootstrap
theorems for probabilities that sums of centered high-dimensional
random vectors hit rectangles and sparsely convex sets. Specifically,
we derive Gaussian and bootstrap approximations for the probabilities
$\Pr(n^{-1/2}\sum_{i=1}^n X_i\in A)$ where $X_1,\dots,X_n$ are
independent random vectors in $\R^p$ and $A$ is a rectangle, or, more
generally, a sparsely convex set, and show that the approximation
error converges to zero even if $p=p_n\to \infty$ as $n \to \infty$
and $p \gg n$; in particular, $p$ can be as large as $O(e^{Cn^c})$ for
some constants $c,C>0$. The result holds uniformly over all
rectangles, or more generally, sparsely convex sets, and does not
require any restriction on the correlation structure among coordinates
of $X_i$.  Sparsely convex sets are sets that can be represented as
intersections of many convex sets whose indicator functions depend
only on a small subset of their arguments, with rectangles being a
special case. This talk is based on joint work with Victor
Chernozhukov (MIT) and Denis Chetverikov (UCLA).

----------------------------------------------------------------------------------

Organizers:
Masanobu TANIGUCHI (Waseda Univ.), Kiyoshi INOUE (Waseda Univ.),
Yoichi MIYATA (Takasaki Econ Univ.) & Xiaoling DOU (Waseda Univ.)
Supported by Kiban (A) (23244011) (M. Taniguchi)

(i) 3月2日、3日: 55号館S棟2階 第3会議室
(ii) 3月4日: 55号館N棟1階　第1会議室

Program

March 2
13:30 - 13:40: Masanobu TANIGUCHI (Waseda Univ.)

13:40 - 14:10: Fumiya AKASHI (Waseda Univ.)
Higher-order asymptotic properties of generalized empirical likelihood estimator for alpha-stable processes

14:10 - 14:40: Yoichi NISHIYAMA (Inst. Stat. Math. Tokyo)
A stochastic maximal inequality, monotone convergence arguments, and related topics

14:40 - 15:10: Satoshi KURIKI (Inst. Stat. Math. Tokyo), with Hsien-Kuei Hwang
A generalization of Anderson-Darling goodness-of-fit statistic based on multifold integrated empirical distribution functions

15:10 - 15:30: Coffee break

15:30 - 16:10: Stanislav VOLGUSHEV (Ruhr-Univ. Bochum), with Holger Dette, Marc Hallin and Tobias Kley
Quantile spectral analysis

16:10 - 16:50: Qi-Man SHAO (The Chinese Univ. Hong Kong)
Perspective of self-normalized limit theory

16:50 - 17:30: Marco LIPPI (Einaudi Inst. Economics & Finance), with Mario Forni, Alessandro Giovannelli and Stefano Soccorsi
Dynamic factor models with infinite dimensional factor space. Forecasting US monthly macroeconomic series.

March 3
10:00 - 10:30: Yan LIU (Waseda Univ.)
Empirical likelihood methods for quantile regression with long range dependent errors

10:30 - 11:00: Xiaoling DOU (Waseda Univ.), with Satoshi Kuriki, Gwodong Lin and Donald Richards
Baker's distribution and the B-spline copula

11:00 - 11:20: Coffee Break

11:20 - 11:50: Toshio HONDA (Hitotsubashi Univ.), with Ming-Yen Cheng and Jialiang Li
Efficient estimation in semivarying coefficient models for longitudinal/clustered data

11:50 - 13:30: Lunch

13:30 - 14:00: Shu-Hui YU (National University of Kaohsiung)
Toward optimal averaging in regression models with time series errors

14:00 - 14:40: Xiaofeng SHAO (Univ. Illinois)
Martingale difference correlation and high dimensional feature screening

14:40 - 15:20: Ching-Kang ING (Inst. Stat. Science, Academia Sinica)
Group and variable selection in high-dimensional regressions

15:20 - 15:40: Coffee Break

15:40 - 16:20: Holger DETTE (Ruhr-Univ. Bochum)
Detection of multiple structural breaks in multivariate time series

16:20 - 17:00: Marc HALLIN (ECARES, Université libre de Bruxelles)
Generalized dynamic factor models and volatilities

18:00 -:          Buffet-style party (Cafeteria; Basya-Michi)

March 4
10:00 - 10:30: Yoichi MIYATA (Takasaki city Univ. of Econ.)
The validity of Bayesian information criteria in misspecified models

10:30 - 11:00: Tomoyuki AMANO (Wakayama Univ.), with Masanobu Taniguchi (Waseda Univ.)
Control variate method for time series

11:00 - 11:30: Hiroaki OGATA (Tokyo Metropolitan Univ.)
Stationary circular time series

11:30 - 12:00: Kiyoshi INOUE (Waseda Univ.)
Precision of estimators for common parameters from several populations

12:00 - 13:30: Lunch

13:30 - 14:00: Kenta KOIZUMI and Hiroshi SHIRAISHI (Keio Univ.)
Statistical estimation for optimal dividend barrier

14:00 - 14:30: Kenichiro TAMAKI (Waseda Univ.)
One-step time series model-building by empirical likelihood

14:30 - 15:00: Shunsuke Sakai and *Junichi Hirukawa (Niigata Univ.)
Rank tests for an ARMA model against other tv-ARMA models

15:00 - 15:20: Coffee Break

15:20 - 15:50: Yasutaka SHIMIZU (Waseda Univ.)
LSE-type estimation for stochastic processes with small Levy noise

15:50 - 16:20: Ryozo MIURA (Hitotsubashi Univ.)
Asymptotic theory of R-estimators from iid to weakly dependent observations: the case of one sample models and simple linear regression models with generalized Lehmann’s alternative models

16:20 - 17:00: Herbert HEYER (Univ. Tuebingen)
Information functionals and applications to random walks and statistics

17:00 - 17:10: Takeru SUZUKI (Waseda Univ.)

18:00 -:          Party (Further details will be announced later)

---------------------------------------------------------------------------------------------------

Title: Robustness in the context of ordinal response models.
Speaker: Anna Clara Monti,   University of Sannio,  Italy

---------------------------------------------------------------------------------------------------

(1) 13:00 - 14:30

Opportunities and Challenges

(2) 14:30 - 16:00

(3) 16:00 - 17:30

18:00-   ビュッフェ形式懇親会　於　馬車道

(3) の講演に関する問い合わせは、鈴木武 <tasuzuki@waseda.jp>　まで
お願いします。

---------------------------------------------------------------------------------------------------

Title: Recent developments in estimation for CO-GARCH(1,1) models
Speaker: Ilia Negri  (Univ. Bergamo, Italy)

Abstract:
COGARCH models are continuous time version of the well known GARCH models of financial returns.
It turns out that COGARCH(1,1) captures the so called stylized facts of volatility:
is random and has jumps; has heavy-tailed margins; has cluster in the extremes (volatility clustering).
In this talk Method of Moments and Pseudo Maximum Likelihood estimators are presented for such COGARCH(1,1) models
and it is shown how the method of Prediction-Based Estimating Functions, that can be applied to this model
if the higher order structure of the process is clarified, outperforms the other available estimation methods.

---------------------------------------------------------------------------------------------------

(i) 14:00 - 15:30
<br>
Abnormal volume effects on the CAPM with heteroskedasticity:
A quantile regression approach

Cathy W.S. Chen  (Feng Chia University, Taiwan)

(ii) 15:30 - 17:00
LASSO estimation of threshold autoregressive models

Ngai Hang Chan (Chinese University of Hong Kong, Hong Kong)

17:30 -  馬車道で立食式懇親会

---------------------------------------------------------------------------------------------------

Date: July 23 (Wed), 2014 15:45−17:30

Location: Nishi-Waseda Campus, Building 63-1st Floor Meeting Room

(1) 15:45−16:30

Spectral envelope analyses for sequence data

Solvang Hiroko Kato, Institute of Marine Research, Norway

(2) 16:30−17:30

Distribution of the sum-of-digits function of random integers: a survey

Hsien-Kuei Hwang, Institute of Statistical Science, A cademia Sinica, Taiwan,
( Cowork with Louis H. Y. Chen and Vytas Zacharovas).

なお、講演終了後、18:00より馬車道でビュッフェ形式の小宴を予定していますの で、ご参加ください。

------------------------------------------------------------------------------------------

Date: June 25 (Wed), 2014 15:00 — 17:00

Location: Nishi-Waseda Campus, Building 63-1st Floor Meeting Room

（１）　１５：００−１６：００

ソルベンシーマージン比率の代替指標と生保破綻の分析

（２） １６：００−１７：００

The Holistic Balance Sheet Approach and Evaluation of Employer
Covenant for Occupational Pensions in Europe

なお、講演終了後、１７：３０より馬車道でビュッフェ形式の小宴を予定していますの で、ご参加ください。

------------------------------------------------------------------------------------------

Date: May 28 (Wed), 2014 15:00 — 17:00

Location: Nishi-Waseda Campus, Building 63-1st Floor Meeting Room

（１）　１５：００−１５：５０

データサイエンスのこれまでとこれから

（２） １６：００−１６：３０

Asymptotic Theory of Parameter Estimation by a Function Based on Interpolation Error

（３）１６：３０−１７：１０

なお、講演終了後、１７：３０よりビュッフェ形式の小宴を予定していますので、ご参 加ください。

------------------------------------------------------------------------------------------

２０１４年４月１６日（水）１５：００−１７：００

Location: Nishi-Waseda Campus, Building 63-1st Floor Meeting Room

（１）　１５：００−１５：３０
QTL解析における影響分析

早稲田大学国際教育センター　　Dou Xiaoling

（２） １５：３０−１６：１０
Default risk analysis with ruin theory

早稲田大学理工学術院　　清水泰隆

（３）　１６：２０−１７：００
公的年金運用の改革−確率的なリスク制約概念の導入とその技術的対応について−

年金積立金管理運用独立行政法人（GPIF）　山下　隆

なお、講演終了後、１７： ３０よりビュッフェ形式の小宴を予定していますので、ご参加ください。

------------------------------------------------------------------------------------------

Waseda International Symposium on “Stable Process, Semimartingale, Finance & Pension Mathematics”

２０１４年３月３日ー５日 (March ３ー５, 2014)

Location: Nishi-Waseda Campus, Building 55S-2th Floor Meeting Room 3

Organizers: Masanobu Taniguchi (Waseda Univ.), Dou Xiaoling (ISM) and Kenta Hamada (Waseda Univ.)
Waseda University, (map http://www.sci.waseda.ac.jp/eng/access/)

Supported by Kiban (A) (23244011) (M.Taniguchi)
& Government Pension Investment Fund (GPIF), Japan

Program (* speaker )

March 3, 2014

13:00 - 14:40 : Chaired by X. Dou
13:00 - 13:30
(1) Generalized Periodogram and Its Statistical Inference for Time Series
Yan Liu (Waseda Univ.)

13:30 - 14:10
(2) Dimension reduction for locally stationary time series factor models
Junichi Hirukawa (Niigata Univ.)

14:10 - 14:50
(3) Estimation of autocopula with estimating function approach
Hiroaki Ogata (Waseda Univ.)

Coffee Break

15:10 - 17:20 : Chaired by J. Hirukawa
15:10 - 15:50
(4) Semiparametric statistics with infinite-dimensional martingales: Bridges between a stochastic maximal inequality and Cox’s         regression model
Yoichi Nishiyama (Inst. Statist. Math., Tokyo)

15:50 - 16:30
(5) Parameter change problem for diffusion processes
Ilia Negri (Univ. Bergamo)

16:30 - 17:20
(6) Inference for change point problems for fractional diffusion processes
B.L.S. Prakasa Rao (Univ. Hyderabad Campus)

March 4, 2014
9:30 - 10:50 : Chaired by T. Mikosch
9:30 - 10:10
(7) Empirical likelihood ratio for symmetric alpha-stable processes
Fumiya Akashi*, Yan Liu and Masanobu Taniguchi (Waseda Univ.)

10:10 - 10:50
(8) EM algorithms for estimating the Bernstein copula
Xiaoling Dou* (Inst. Stat. Math.), Satoshi Kuriki, Gwo Dong Lin and Donald Richards

Coffee Break

11:00 - 12:30 : Chaired by I. Negri

11:00 - 11:40
(9) LAD-based estimation of locally stable Ornstein-Uhlenbeck processes
H. Masuda (Kyushu Univ.)

11:40 - 12:30
(10) Nonparametric independence screening and structural identification for ultra-high dimen- sional longitudinal data
Ming-Yen Cheng, Toshio Honda* (Hitotsubashi Univ.), Jialiang Li and Heng Peng

Lunch

13:40 - 15:20 : Chaired by C. Kluppelberg
13:40 - 14:30
(11) Distributions of the maximum likelihood and minimum contrast estimators associated with the fractional Ornstein-Uhlenbeck     process
Katsuto Tanaka (Gakusyuin Univ.)

14:30 - 15:20
(12) Extremogram and Ex-Periodogram for heavy-tailed time series
Thomas Mikosch* (Univ. Copenhagen), Richard A. Davis (Columbia Univ.) and Yuwei Zhao

Coffee Break

15:40 - 17:20 : Chaired by M.Taniguchi

15:40 - 16:30
(13) Continuous-time GARCH models Claudia Kluppelberg (Munich Univ. Technology)

16:30 - 17:20
(14) Asymptotic Theory for the Sample Covariance Matrix of a Heavy-Tailed Multivariate Time Series
Richard A. Davis (Columbia Univ.)

Buffet Style Dinner
18:30 - Basyamichi (63 building 1st floor)

March 5, 2014
10:00 - 12:10 : Chaired by R. Davis
10:00 - 10:40
(15) Asymptotics of Realized Volatility with Non-Gaussian ARCH(∞) Microstructure Noise
Hiroyuki TANIAI*, T. Usami, N. Suto and M. Taniguchi (Waseda Univ.)

10:40 - 11:20
(16) Review of Statistical Portfolio Theory
Hiroshi Shiraishi (Jikei Medical Univ.)

11:20 - 12: 10
(17) Bayesian estimation of smoothly mixing time-varying parameter GARCH models
Cathy W. S. Chen* (Feng Chia Univ), Richard Gerlach and Edward M. H. Lin

------------------------------------------------------------------------------------------

High Dimensional Statistical Analysis and Related Topics

２０１４年１月６日ー７日 (January 6-7, 2014)

Location: Waseda University  Building 63-1 Meeting Room

(Supported by (A) 23244011( M.Taniguchi, Waseda Univ. )

Program

January 6, 2014

13:30 - 14:15 : Discussion on “ High Dimensional Statistical Analysis “
Chaired by Masanobu Taniguchi ( Waseda Univ. )

14:15 - 15:00
Efficient influence function of coefficient functions in quantile regression
By Hiroyuki Taniai ( Waseda Univ. )

15:00 - 15:30   Coffee Break

15:30 - 16:15
Locally stationary time series factor models
By Junichi Hirukawa ( Niigata Univ. )

16:15 -17:00
Generalized Least Squares Model Averaging,
Qingfeng Liu ( Otaru University of Commerce ) , Ryo Okui ( Kyoto Univ. )
and Arihiro Yoshimura ( Kyoto Univ. )

17:30 -
Buffet Style Dinner

January 7, 2014

10:30 - 11:00
Robust spectral estimation in time series analysis
By Yan Liu ( Waseda Univ. )

11:00- 11:30
Nonparametric LAN approach for frequency domain GMM-type hypothesis
testing
By Fumiya Akashi ( Waseda Univ. )

11:30 - 12:15 : General Discussion

12:15 - 13:45 : Lunch

13:45 - 14:45
Testing second order dynamics for autoregressive processes in presence of time-varying variance.
By Hamdi Raissi  ( Univ. Europeenne de Bretagne, France )

14:45 - 15:00: Coffee Break

15:00- 16:00
Nonparametric estimation of probability density functions for irregularly observed spatial data
By Zudi Lu  ( University of Southampton, U.K. )

16:00- 17:00
The dynamic structure of high-dimensional factor models
By Marco Lippi  ( Universit a di Roma "La Sapienza" and EIEF )

------------------------------------------------------------------------------------------

(Oct. 1st, 3:00pm to 5:00pm)

(Location: Waseda University, Nishi-Waseda Campus, Room 63-1-Meeting Room)

連続時間モデルに対するポートフォリオ推定問題
( Portfolio Estimation for Continuous Time Models)

白石　博
慈恵医科大学( Shiraishi, H., Jikei Medical Univ.)

Optimal prediction-based estimating function for COGARCH(1,1) models

Ilia Negri
Department of Engineering、University of Bergamo (Italy)

(3) Small Buffet Party:  17:30 - 19:30

------------------------------------------------------------------------------------------

２０１３ 年９月３日(September 3,2013)（火）　１６：００−１７：００

（１） 　16:00-17:00

なお、講演終了後、ビュッフェ形式の小宴を予定していますので、ご参加ください。

---------------------------------------------------------------------------------------

２０１３年７月３０日 (Juｌｙ 30, 2013)（火）１５：３０−１６：３０

Hsien-Kuei Hwang

---------------------------------------------------------------------------------------

２０１３年７月３１日 (Juｌｙ 31, 2013)（水）１５：００−１７：００

（１） １５：００−１６：００
Consideration on a serial correlation
早稲田大学　小方　浩明 ( Ogata, H., Waseda Univ.)

（２）１６：００−１７：００
Performance of time-varying volatility estimation methods for portfolio management
ＧＰＩＦ　山下　隆　( Yamashita, T., GPIF)

---------------------------------------------------------------------------------------

２０１３年６月１８日 (June 18, 2013)（火）１５：３０−１７：００

なお、講演終了後、ビュッフェ形式の小宴を予定していますので、ご参加ください。

---------------------------------------------------------------------------------------

２０１３年５月２１日(May 21, 2013)（火）１４：３０−１７：００

（１）　１４：３０−１５：１５
Empirical likelihood approach for discriminant analysis
of stable linear processes
早稲田大学理工学研究科　　明石 郁哉
(Fumiya Akashi, Waseda Univ.)

（２） １５：１５−１６：００
Asymptotic moments of symmetric　self-normalized sums
早稲田大学理工学研究科　　劉　言
(Yan Liu, Waseda Univ.)

（３）　１６：００−１７：００
Efficient inference for regression quantiles via Z-estimation
早稲田大学国際教養学部　　谷合　弘行
(Hiroyuki Taniai, Waseda Univ.)

---------------------------------------------------------------------------------------

２０１３年４月２３日(April 23, 2013)（火）１5：００−１７：００

(１) １５：００−１６：００
Non-regular estimation for time series
早稲田大学　谷口　正信

(２) １６：００−１７：００
二変量順序統計量の相関構造とその応用
統計数理研究所　　Dou Xiaoling

---------------------------------------------------------------------------------------

２０１３年３月２８日(March 28, 2013)（木）１４：００−１７：００

(1) 14:00 - 15:30
CUB models: properties, applications and robustness issues.
Anna Clara Monti ( University of Sannio, Italy).

(2) 15:30 - 17:00
Thomas J. DiCiccio ( Cornell University, USA ).

---------------------------------------------------------------------------------------

２０１３年１月２９日(Jan. 29, 2013)（火）１５：００−１７：００

（１） 　１５：００−１６：００
Alex Petkovic ( Waseda University )

Title : On the local likelihood estimator

（２） 　１６：００−１７：００
広島大学　柳原宏和 ( Yanagihara, H. Hiroshima Univ.)

Title : Theoretical and numerical considerations of properties of the variable selection in normal multivariate linear regression models by an information criterion minimization method

---------------------------------------------------------------------------------------

２０１２年１１月２８日(Nov. 28, 2012)（水,Wed）１５：００−１７：００

（１） 15：00−16：00 ：

Recent developments of insurance ruin theory: Gerber-Shiu Analysis
大阪大学　清水　泰隆 ( Shimizu, Y., Osaka Univ.)

（２） 16:00−17:00 ：

Quantile regression estimator for GARCH models
Sangyeol Lee, (Seoul National University)

---------------------------------------------------------------------------------------

２０１２年１０月３０日(Oct. 30, 2012)（火）１５：００−１７：００

（１） 15：00−16：00 ：

Analysis of CL and estimating function estimators for financial time series models
和歌山大学　天野　友之 ( Amano, T., Wakayama Univ.)

（２）16:00−17:00 ：

An estimation techniqe for Jamp-diffusion process using MLE based jump detection scheme
GPIF　山下　隆　( Yamashita, T., Government Pension Investment Fund)

---------------------------------------------------------------------------------------

２０１２年９月２５日(September 25, 2012)（火）１4:00−17:00

（１） 14：00−15：00 ：

Grapgical Representation of Multiple Regression Analysis.
早稲田大学　石村　友二郎 ( Ishimura, Y., Waseda Univ.)

（２）15:00−16:00 ：

いろいろなポートフォリオ推定理論について。 　　 ( Various Estimation Theory for Portfolios)
慈恵医科大学　白石　博 ( Shiraishi, H., Jikei Medical Univ.)

（１） 16：00−17：00 ：

周辺尤度に対するラプラス近似の漸近誤差とその周辺。 　　　( Asymptotic Error Evaluation of Laplace Approximation for Marginal Likelihood and Its Related Fields )
高崎経済大学　宮田　庸一( Miyata, Y., Takasaki City Univ. Economicsi)

---------------------------------------------------------------------------------------

（１） 15：00−16：00 ：

Theory & Applications for Statistical Science.
早稲田大学　谷口　正信 ( Taniguchi, M., Waseda Univ.)

（２）16:00−17:00 ：

最近の欧州公的年金ポートフォリオ策定手法の紹介 ( Introduction to Recent Methods for European Government Pension Portfolios)
GPIF　山下　隆　( Yamashita, T., Government Pension Investment Fund)

---------------------------------------------------------------------------------------

（２）13 : 00−14 : 00 ：

Various Problems in Financial Time Series Analysis
早稲田大学　長幡　英明　 ( Nagahata, H., Waseda Univ.)
早稲田大学　宇佐美　友梨 ( Usami, U., Waseda Univ.)
早稲田大学　鈴木　卓哉　 ( Suzuki, T., Waseda Univ.)
早稲田大学　横山　明日希 ( Yokoyama, A.,Waseda Univ.)
早稲田大学　谷口　正信 ( Taniguchi, M., Waseda Univ.)

（２）14 : 00−15 : 00 ：

The Detection of Stress Using the Voice Analysis
早稲田大学　石村　友次郎 ( Ishimura, T., Waseda Univ.)

（3） 15：00−16：00 ：

Productivity of Service Providers: Microeconometric measurement in the case of hair salons
経済産業研究所　小西　葉子 ( Konishi, Y., RIETI)

（3） 16：00−17：00 ：

“Soft” Benefit Promises　of Occupational Pensions　and Intergenerational Fairness
農業者年金基金　清水　信広 ( Shimizu, N., NFPF )

---------------------------------------------------------------------------------------

（２）13 : 00−14 : 00 ：

Statistical properties for long-horizon investors's portfolio linking with macroeconomic indices performance
Takashi Yamashita ( Government Pension Investment Fund (GPIF) )

（２）14 : 00−15 : 30 ：

A simple model for vast panels of volatilities
David Veredas (Univ. Libre de Bruxelles)

（3） 15：30−17：00 ：

Pseudo-Gaussian and Rank-Based Optimal Tests for Random Individual Effects in Large n Small T Panels
Marc Hallin (Univ. Libre de Bruxelles)

---------------------------------------------------------------------------------------

（１） 15：00−16：00 ：

Modeling financial data with multivariate stable distributions.
早稲田大学　小方　浩明 ( Ogata, H., Waseda Univ.)br>

（２）16:00−17:00 ：

年金制度の自動安定化メカニズムと世代間の公正（Automatic Stabilization Mechanism and Intergenerational Equity in Pension System)
農業者年金基金　清水信広( Shimizu, N., National Farmers Pension Fund)

---------------------------------------------------------------------------------------

（２）13 : 30−14 : 30 ：

Asymptotic Efficiency in Dynamic Panel Data Models When Both N and T are Large
京都大学経済研究所　岩倉　相雄 ( Iwakura, H., Kyoto Univ.)

（２）14 : 30−15 : 30 ：

クレーム総額の時系列モデルについて（Time Series Models for Total Claim Amount)
新潟大学自然科学系　蛭川　潤一（ Hirukawa, J. Niigata Univ.)

（3） 15：30−16：30

臨床研究で使われる統計解析手法の紹介 (Introduction of statistical methods for clinical reserch)
第一三共株式会社研究開発本部・データサイエンス部・統計解析グループ：塩境　一仁( Shiosakai, K., Daiichi-Sankyo Pharmaceutical Company)

---------------------------------------------------------------------------------------

（１） 15：00−15：50 ：

GPIF基本ポートフォリオの策定方法 (Formulation Method for GPIF fundamental portfolios)
山下 隆 (T. Yamashita)　( GPIF )

（２）16:00−16: 50 ：

Linear regression with deterministic regressors and unit root in the　variance
Alex Petkovic (Waseda University)

---------------------------------------------------------------------------------------

（１） 15：00−16：00 ：

Semiparametric estimation for diffusion processes: pseudo-likelihood method and Bays method
統計数理研究所　西山　陽一　( Nishiyama, Y., Inst. Statist. Math.)

（２）16:10−17:00 ：

掛金の経済価値を制御する方法(Economic Values of Contribution Cashflows and Measures to Bring the EVs under Control)
農業者年金基金　清水　信広　( Shimizu, N., National Farmer Pension Fund)

---------------------------------------------------------------------------------------

（１） 15：00−15：40 ：

Statistical Portfolio Estimation Under the Utility Function Depending on Exogenous Variables and Its Applications
早稲田大学　濱田　健太 ( Hamada, K. (D1), Waseda Univ.)

（２）16:00−16:40 ：

運用関係指標（資産運用収益率、賃金上昇率など）の統計的性質( Statistical Properties of Indices on Working Assets )
GPIF　山下　隆　( Yamashita, T., Government Pension Investment Fund)

---------------------------------------------------------------------------------------

（１） 13：30−14：15 ：

Statistical Estimation of Optimal Portfolios for Dependent Returns.
早稲田大学　谷口　正信 ( Taniguchi, M., Waseda Univ.)

（２）14:15−15:00 ：

Bootstrap Estimation of Optimal Portfolios
慈恵医科大学　白石　博 ( Shiraishi, H., Jikei Medical Univ.)

（２）15:30−16:00 ：

最近の公的年金投資の諸問題( Recent Problems for Government Pension Investment)
GPIF　山下　隆　( Yamashita, T., Government Pension Investment Fund)

トップページへ