2015 Fiscal Year Final Research Report
Theory and application of a Bayesian information criterion
| Project/Area Number |
24740069
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
General mathematics (including Probability theory/Statistical mathematics)
|
|---|
| Research Institution | Takasaki City University of Economics |
|---|
Principal Investigator |
Miyata Yoichi 高崎経済大学, 経済学部, 准教授 (10514250)
|
|---|
| Project Period (FY) |
2012-04-01 – 2016-03-31
|
| Keywords | ラプラス近似 / ベイズ統計学 / 情報量規準 |
|---|
| Outline of Final Research Achievements |
When applying Laplace's method to approximate an integral, we require an exact mode of its integrand. We derive a Laplace approximation using an asymptotic mode of an asymptotic mode instead of the exact mode, and present some ways to establish asymptotic modes with a desirable order.
The class of the asymptotic modes is wide and includes consistent estimators with some convergence rate and a true parameter.
|
| Free Research Field |
統計学（漸近理論）
|
