2013 Fiscal Year Final Research Report
A reformulation of Bayesian statistics as pediction theory and its applications
| Project/Area Number |
23300104
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Statistical science
|
|---|
| Research Institution | The University of Tokyo |
|---|
Principal Investigator |
KOMAKI Fumiyasu 東京大学, 情報理工学(系)研究科, 教授 (70242039)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
MOROHOSHI Hozumi 政策研究大学院大学, 政策研究科, 教授 (10272387)
|
|---|
| Co-Investigator(Renkei-kenkyūsha) |
TANAKA Fuyuhiko 大阪大学, 基礎工学研究科, 准教授 (90456161)
|
|---|
| Project Period (FY) |
2011-04-01 – 2014-03-31
|
| Keywords | 予測理論 / ベイズ統計 / 情報量 |
|---|
| Research Abstract |
Constructing methods for prior distributions in Bayesian statistics based on maximization of the conditional mutual information are investigated. In particular, statistical testing problems are formulated as a prediction problem by setting the null hypothesis as 0 and the alternative hypothesis as 1. It is shown that prior distributions that have not been considered in previous studies naturally appear. Numerical algorithms for maximizing the mutual information are developed.
|
