2012 Fiscal Year Final Research Report
New Development of Statistical Theory in Multivariate Data Analysisand Its Applications
Project/Area Number |
22500259
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Single-year Grants |
Section | 一般 |
Research Field |
Statistical science
|
Research Institution | Hiroshima University |
Principal Investigator |
|
Co-Investigator(Kenkyū-buntansha) |
YANAGIHARA Hirokazu 広島大学, 大学院・理学研究科, 准教授 (70342615)
|
Project Period (FY) |
2010 – 2012
|
Keywords | モデル選択 / 多変量回帰モデル / 成長曲線モデル / 正準相関分析 / 判別分析 / 高次元漸近理論 / 多項ロジット回帰 / 環境データ分析 |
Research Abstract |
In this project we tackled the following important problems in multivariate statistical analysis: (1) Development of statistical inference in quantification methods, (2) Proposals of high-dimensional model selection criteria and study on their properties, (3) Development of statistical inference in analysis of repeated measurement data, (4) Development of statistical inference for multivariate non-linear models, (5) Development of high-dimensional statistical methods and asymptotic theory. Especially, we proposed high-dimensional AIC, etc. Further, we showed that they have consistency property.
|