2007 Fiscal Year Final Research Report Summary
Information geometry and Bayesian inference for high-dimensional parametric and semi-parametric models
| Project/Area Number |
17500178
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Statistical science
|
|---|
| Research Institution | The University of Tokyo |
|---|
Principal Investigator |
KOMAKI Fumiyasu The University of Tokyo, Graduate School of Information Science and Technology, Associate Professor (70242039)
|
|---|
| Project Period (FY) |
2005 – 2007
|
| Keywords | Bayesian theory / prediction / information geometry |
|---|
| Research Abstract |
Prediction and inference methods for high-dimensional models and semiparametric models have been investigated. It is shown that the model manifold of the Neyman-Scott model is the space with constant negative curvature. The Neyman-Scott model is formulated as a transformation group model. A predictive density dominating the best invariant predictive density has been constructed by using information geometry. Furthermore, empirical likelihood methods for semiparametric models have been studied. Empirical likelihood methods were formulated in the framework of information geometry.
Prediction methods for statistical problems with multiplicity have also been studied.
|
Research Products
(30 results)
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
[Presentation] Risk sensitive decision networks.2005
Author(s)
Kobayashi, K. and Komaki, F
Organizer
Second Latin American Congress on Bayesian Statistics
Place of Presentation
San Jose'del Cabo, Baja California, Mexico
Year and Date
20050206-10
Description
「研究成果報告書概要(和文)」より
-
[Presentation] Risk sensitive decision networks2005
Author(s)
Kobayashi, K. and Komaki, F.
Organizer
Second Latin American Congress on Bayesian Statistics
Place of Presentation
San Jose' del Cabo, Baja California, Mexico.
Year and Date
20050206-10
Description
「研究成果報告書概要(欧文)」より
-
-
