|Day & Time||19th May, 2017 15:00-16:00|
|Venue||Room C816, Building of the Department of Science|
|Lecturer||Prof. Yasuhiro OMORI (University of Tokyo)|
|Presentation Title||Multivariate stochastic volatility model with realized
volatilities and pairwise realized correlations
|Abstract||Although stochastic volatility and GARCH models have been successful to
describe the volatility dynamics of univariate asset returns, their natural
extension to the multivariate models with dynamic correlations has been
difficult due to several major problems. Firstly, there are too many
parameters to estimate if available data are only daily returns, which
results in unstable estimates. One solution to this problem is to
incorporate additional observations based on intraday asset returns such as
realized covariances. However, secondly, since multivariate asset returns are not traded synchronously, we have to use largest time intervals so that all asset returns are observed to compute the realized covariance matrices, where we fail to make full use of available intraday informations when there are less frequently traded assets. Thirdly, it is not straightforward to guarantee that the estimated (and the realized) covariance matrices are positive definite.
Our contributions are : (1) we obtain the stable parameter estimates for dynamic correlation models using the realized measures, (2) we make full use of intraday informations by using pairwise realized correlations, (3) the covariance matrices are guaranteed to be positive definite, (4) we avoid the arbitrariness of the ordering of asset returns, (5) propose the flexible correlation structure model (e.g. such as setting some correlations to be identically zeros if necessary), and (6) the parsimonious specification for the leverage effect is proposed. Our proposed models are applied to daily returns of nine U.S. stocks with their realized volatilities and pairwise realized correlations, and are shown to outperform the existing models with regard to portfolio performances.
March 5 (Sun), 2017
National Graduate Institute For Policy Studies, Tokyo
Mr. Shota OCHIAI (Graduate student, Hiroshima University) earned the prize named “Student Presentation Award” at
11th Japan Statistical Society spring time meeting.
The title of his poster is “L0 penalty vs L1 penalty
-Focusing on variable selection in discriminant“.
The Society was held at National Graduate Institute For Policy Studies in Tokyo on March 5, 2017.
L0 penalty vs L1 penalty -Focusing on variable selection in discriminant-
Shota OCHIAI, Tomoyuki NAKAGAWA,
Hirokazu YANAGIHARA, Yasunori FUJIKOSHI (Hiroshima University)
We held a training session about “R” (computer software) named “Second R” on February 18, 2017 in Hiroshima University. (Lecturer: Prof. Mariko Yamamura)
This workshop was aimed at improving the skill of statistical analysis, the second time (the third time as the number of times) following “the first time R” held last year.
About 50 participants gathered from inside and outside the campus at the venue.
Prof. Mariko Yamamura, a member of the Graduate school of Education, was a lecturer. The theme was “drawing graphs“, and the participants learned how to draw box plot diagrams, histograms and other drawing methods, and learned advanced techniques such as changing the color of graphs, superimposing graphs, color coding by groups, and so on .
The students acquired skills while receiving assistance from the teaching assistant.
* “Second R” recruitment page (the application was closed/Japanese only)
|Day & Time||December 17, 2016 9:10-17:10|
|Venue||Hiroshima University Faculty Club, 2F, Reception Hall|
Members of SSRC held international conference named “Hiroshima Conference on Statistical Science 2016” on December 17 at Higashi Hiroshima campus.
We invited some guest speakers from other countries and they gave a lecture at this conference. Not only members of SSRC but also graduate students joined our conference.
|Day & Time||20th December, 2016 10:30-12:00|
|Venue||Room 105, Building of the Faculty of Engineering|
|Lecturer||Dr. Takumi Kobayashi|
|Presentation Title||Image recognition by co-occurrence features|
Prof. Kazuhiko Hayakawa will hold “Kansai Keiryo Keizaigaku Kenkyukai (KKKK)” on January 7(Sat) and 8(Sun), 2017.
If you want to have more information, Please click here. (Sorry, Japanese only).
|Day & Time||January 7(Sat)- 8(Sun), 2017|
|Venue||2nd Floor, Higashi-Senda Innovative Research Center, Higashi Senda Campus|
We are going to hold “Biometrics Seminar” on December 12 at Kasumi campus.
-Date: December 12 (Mon), 16:00-
-Venue: Kasumi Biomedical Research Building, Seminar Room 433,
Research Institute for Radiation Biology and Medicine
|16:00-17:00||Prof. Kunihiko Takahashi (Nagoya University)
“Multiple-cluster detection test for disease clustering”
|17:00-18:00||Dr. Yuri Ito (Osaka Medical Center for Cancer and Cardiovascular Diseases)
“Trends in Socioeconomic Inequalities in Cancer in Japan using Areal Deprivation Index”
|18:00-19:00||Dr. Keisuke Fukui (Osaka Medical Center for Cancer and Cardiovascular Diseases)
“Comparison between prefectures by the trend analysis of cause specific mortality across occupations”
Hiroshima Conference on Statistical Science 2016
|Date : December 17, 2016|
|Place : Hiroshima University Faculty Club, 2F, Reception Hall (→web site)|
|Day & Time||3rd February 2017|
|Venue||Room C816, Building of the Faculty of Science Graduate school of Science|
|Lecturer||Prof. Kazuhiko Kakamu (Kobe University)|
|Presentation Title||Baysian estimation of beta-type distribution parameters based on grouped data|
|Abstract||This study considers the estimation method of generalized beta (GB) distribution parameters based on
grouped data from a Bayesian point of view. Because the GB distribution, which was proposed by McDonald
and Xu (1995), includes several kinds of familiar distributions as special or limiting cases, it performs at least
as well as those special or limiting distributions. Therefore, it is reasonable to estimate the parameters of the GB distribution. However, when the number of groups is small or when the number of parameters increases, it may become difficult to estimate the distribution parameters for grouped data using the existing estimation
methods. This study uses a Tailored randomized block Metropolis–Hastings (TaRBMH) algorithm proposed by Chib and Ramamurthy (2010) to estimate the GB distribution parameters, and this method is applied to one simulated and two real datasets. Moreover, the Gini coefficients from the estimated parameters for the GB distribution are examined.