2010 Fiscal Year Final Research Report
Expanding the regression analysis through the innovative applications of Bayesian methods
Project/Area Number |
20500259
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Single-year Grants |
Section | 一般 |
Research Field |
Statistical science
|
Research Institution | Chuo University |
Principal Investigator |
YANAGIMOTO Takemi Chuo University, 理工学部, 客員教授 (40000195)
|
Project Period (FY) |
2008 – 2010
|
Keywords | 交叉検証法 / 平滑化 / 不適切事前分布 / Bayes法 / DIC / GCV |
Research Abstract |
The assumption of a prior information for a parameter contained in the sampling density is essential, and the use of a proper prior density is obviously desired. This view allows us to pursue fundamental subjects such as the smoothing method. I began with exploring the deviance information criterion (DIC). Our tools for this challenging problem are the use of the e-mixture predictor and the two notions of the unbiasedness of a potential function. Then I attempted to explore a cross-validation criterion (CVC). The induced CVC fortunately shows good performance, and the reasons of performance becomes clear. The results are expected to stimulate our future studies of this subject.
|