Exploring new horizons in statistical inference theory in multivariate analysis

2023 Fiscal Year Final Research Report

• Project/Area Number: 19K11867
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 60030:Statistical science-related
• Research Institution: Osaka Metropolitan University (2022-2023); Japan Women's University (2019-2021)
• Principal Investigator: Konno Yoshihiko 大阪公立大学, 大学院理学研究科, 教授 (00205577)
• Project Period (FY): 2019-04-01 – 2024-03-31
• Keywords: 縮小推定量 / 推定量の評価 / 同時推定問題 / 共通平均問題 / コピュラ / メアアナリシス

Outline of Final Research Achievements

The results include the following.(1) Accuracy evaluation of the estimator in the problem of simultaneous estimation of the mean vector in a complex multivariate normal model when the covariance matrix is unknown.(2) Examine the problem of parameter estimation in meta-analysis in the framework of the common mean estimation problem, propose a reduced estimator, and numerically evaluate its accuracy.(3) Proposal of a new low-rank estimator for estimation problems when the mean matrix of a matrix-type multivariate normal distribution model with a common unknown variance-covariance matrix is low-rank.

Free Research Field

数理統計学

Academic Significance and Societal Importance of the Research Achievements

統計的推測問題に対する理論的な結果は, 本課題がかかわる学問領域において重要な役割を果たす. さらに, 生物統計学への応用も視野に入れた研究成果も含むので, その社会的な意義も高いと思われる.