INFORMATION of SYMPOSIUM

Supported by

Grant-in-Aid for Scientific Research (A) 15H01678 (Project Period: 2015-2019)
"Theories and Methodologies for Large Complex Data"
(Principal Investigator: Makoto Aoshima),
Grant-in-Aid for Challenging Research (Exploratory) 19K22837
(Project Period: 2019-2021)
"Tackling Individualized Modeling with Ultra-High Dimensional Data"
(Principal Investigator: Makoto Aoshima)
Symposium_2017
Title International Symposium on Theories and Methodologies for Large Complex Data
Program/ Flyer Program/ Flyer
Organizers Makoto Aoshima (University of Tsukuba)
Mika Sato-Ilic (University of Tsukuba)
Kazuyoshi Yata (University of Tsukuba)
Aki Ishii (Tokyo University of Science)
Date Nov. 21-23, 2019
Venue Conference Room 406, Tsukuba International Congress Center
Address 2-20-3 Takezono, Tsukuba, Ibaraki 305-0032, Japan
Contents & Purposes Nowadays, large complex data such as high-dimensional data and big data appear in many areas of science. Statistical methodologies for analyzing large complex data have been changing dramatically. Our purpose is to have a fruitful opportunity to discuss these subjects from a broad point of view. In addition, we will invite the following five distinguished researchers and hold a keynote session and a special invited session on Nov. 22, 2019.
Keynote speakers
   Prof. Jeff Yao (The University of Hong Kong)
   Prof. I-Ping Tu (Academia Sinica)
Special invited speakers
   Dr. Ping-Shou Zhong (University of Illinois at Chicago)
   Dr. Joong-Ho Won (Seoul National University)
   Dr. Jörn Schulz (University of Stavanger)
Keywords Large complex data, Big data, High-dimensional statistical analysis, Machine learning, Artificial intelligence, Biostatistics, Bioinformatics, Data mining, Finance, and so on.
Traveling expenses The travel expenses are mainly for shared speakers.
Abstract/ Report We would like speakers to email
(1) abstract (A4 paper, within 10 pages) and
(2) report (A4 paper, within 2 pages)
to the address stated below.
Abstract/ Report Deadline Oct. 31, 2019
Registration/ Abstract submission Kazuyoshi Yata
Institute of Mathematics, University of Tsukuba
1-1-1 Tennodai, Tsukuba, Ibaraki 305-8571, Japan
E-mail: yata [at] math.tsukuba.ac.jp
TEL: +81-29-853-4291
Access Please see THIS PAGE.

INFORMATION of SEMINARS

Supported by

Grant-in-Aid for Scientific Research (A) 15H01678 (Project Period: 2015-2019)
"Theories and Methodologies for Large Complex Data"
(Principal Investigator: Makoto Aoshima),
Grant-in-Aid for Challenging Research (Exploratory) 17K19956
(Project Period: 2017-2018)
"New Developments for Big Data by Non-sparse Modeling"
(Principal Investigator: Makoto Aoshima).
Date November 14, 2018, 3:00 PM-4:10 PM
Venue D509 Institute of Natural Sciences, University of Tsukuba [Access]
Speaker Nitis Mukhopadhyay
(Department of Statistics, University of Connecticut-Storrs)
Title Point Estimation Methods for a Negative Exponential Location:
Illustrations with Infant Mortality and Bone Marrow Data
Abstract   We introduce Stein-type two-stage, modified two-stage, and purely sequential strategies to estimate an unknown location parameter of a negative exponential distribution (with an unknown scale parameter) under a newly defined and modified Linex loss function. We aim at controlling the associated risk function per unit cost (RPUC) by bounding it from above with a positive number ω that is fixed in advance. We emphasize both asymptotic first-order and second-order properties for the modified two-stage and purely sequential estimation strategies.
  In developing asymptotic second-order properties for the modified two-stage and purely sequential methodologies, we heavily rely upon basic ideas rooted in Mukhopadhyay and Duggan (1997) and nonlinear renewal theory from Lai and Siegmund (1977, 1979), Woodroofe (1977), and Ghosh et al. (1997), respectively.
  Then, we take to extensive data analysis carried out via simulations when requisite sample sizes may range from small to moderate to large. We find that the Stein-type two-stage estimation methodology oversamples significantly and yet the achieved risk may not be close to ω. On the other hand, both modified two-stage and purely sequential estimation strategies perform remarkably well.
  Next, we will validate the major theoretical first-order and second-order properties through simulated data. The methodologies will also be illustrated using real datasets from health studies, namely, infant mortality data and bone marrow data.
Keywords Location parameter; Modified Linex loss; Modified two-stage; Purely sequential; Real data illustrations; Risk per unit cost; Simulations; Two-stage.

Meetings and workshops that we helped organize

  1. The 6th Institute of Mathematical Statistics Asia Pacific Rim Meeting
    Melbourne, Australia, January 5-8, 2021
    http://ims-aprm2021.com/
  2. The 4th International Conference on Econometrics and Statistics
    South Korea, July 20-22, 2020
    http://cmstatistics.org/EcoSta2020/
  3. The 3rd International Conference on Econometrics and Statistics
    Taiwan, June 25-27, 2019
    http://cmstatistics.org/EcoSta2019/index.php
  4. The 5th Institute of Mathematical Statistics Asia Pacific Rim Meeting
    Singapore, June 26-29, 2018
    https://ims-aprm2018.stat.nus.edu.sg/
  5. The 4th Conference of International Society of Nonparametric Statistics
    Italy, June 11-15, 2018
    http://www.isnps2018.it/
  6. Grants-in-Aid for Scientific Research Symposium
    "Statistical Analysis for Large Complex Data -Theories, Methodologies, and Their Applications to the Related Fields-"
    University of Tsukuba, December 1-3, 2017
  7. Grants-in-Aid for Scientific Research Symposium
    "International Symposium on Statistical Analysis for Large Complex Data"
    University of Tsukuba, November 21-23, 2016
  8. The 4th Institute of Mathematical Statistics Asia Pacific Rim Meeting
    Hong Kong, June 27-30, 2016
    http://ims-aprm2016.sta.cuhk.edu.hk/
  9. Grants-in-Aid for Scientific Research Symposium
    "Theories and Methodologies for Large Complex Data: Trends in the Forefront"
    University of Tsukuba, November 16-18, 2015
  10. ISNPS Meeting "Biosciences, Medicine, and novel Non-Parametric Methods"
    Graz, Austria, July 12-15, 2015
  11. Workshop on Statistical Methods for Large Complex Data
    National Sun Yat-sen University, Taiwan, March 12-14, 2015
  12. Grants-in-Aid for Scientific Research Symposium
    "Workshop on Statistical Methods for Large Complex Data"
    University of Tsukuba, November 10-12, 2014
  13. The 3rd Institute of Mathematical Statistics Asia Pacific Rim Meeting
    "Recent Developments in High-Dimensional Inference and Methodologies"
    Howard International House, Taipei, Taiwan, June 30-July 3, 2014
  14. Workshop on Statistics for High-Dimensional and Dependent Data
    National Taiwan University, Taiwan, March 21, 2014
  15. Grants-in-Aid for Scientific Research Symposium
    "Theories and Methodologies for High-Dimensional Data Analysis and their Applications to Related Fields"
    University of Tsukuba, November 25-27, 2013
  16. The 4th International Workshop in Sequential Methodologies
    University of Georgia, U.S.A., July 18-21, 2013
    http://www.stat.uga.edu/IWSM2013
  17. The 7th Japan Statistical Society Spring Meeting
    "Theories and Methodologies in High Dimensional Data Analysis: the Forefront Trends"
    Gakushuin University, March 3, 2013
  18. The 2nd Institute of Mathematical Statistics Asia Pacific Rim Meeting
    "High-Dimensional Inference and Methodologies"
    Tsukuba International Congress Center, July 3, 2012
  19. Grants-in-Aid for Scientific Research Symposium
    "Theories and Methodologies of Statistical Estimation and Their Latest Trends"
    University of Tsukuba, November 7-9, 2011
  20. The 3rd International Workshop in Sequential Methodologies
    Stanford University, California, U.S.A., June 14-16, 2011
  21. Grants-in-Aid for Scientific Research Symposium
    "Statistics for High Dimensional Data -Theories, Methodologies, and Their Applications to the Related Fields-"
    University of Tsukuba, December 14-16, 2009