2010 Fiscal Year Final Research Report
An analytical approach to Bayesian generalized linear models
| Project/Area Number |
20700259
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Single-year Grants |
|---|
| Research Field |
Statistical science
|
|---|
| Research Institution | The Institute of Statistical Mathematics |
|---|
Principal Investigator |
OHNISHI Toshio The Institute of Statistical Mathematics, 大学院・経済学研究院, 准教授 (60353413)
|
|---|
| Project Period (FY) |
2008 – 2010
|
| Keywords | 統計数学 / 一般化線形モデル / Bayes統計学 / 共役事前分布 / Tweedie分布 / 降水量データ / 国際情報交換 / オーストラリア |
|---|
| Research Abstract |
The following three major topics were investigated.
(1) Noting the equality satisfied by the optimal predictive density, we discussed a Bayesian model selection criterion.
(2) We derived duality in the Bayesian estimation from the analytical property of having a conjugate prior.
(3) We investigated a linear mixed model that is based on a location family having a conjugate prior.
As an application study we analyzed the rainfall data of East Australia using a generalized linear model whose underlying distribution is the Tweedie distribution.
|
