| Project/Area Number |
18K18008
|
|---|
| Research Category |
Grant-in-Aid for Early-Career Scientists
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Basic Section 60030:Statistical science-related
|
|---|
| Research Institution | Meiji University (2021-2022)
Hokkaido University (2018-2020) |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2018-04-01 – 2023-03-31
|
| Project Status |
Completed (Fiscal Year 2022)
|
| Budget Amount *help |
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2020: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2019: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2018: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
|
|---|
| Keywords | 数理統計学 / スパース推定 / 情報幾何学 / ベイズ統計 / オッズ比 |
|---|
| Outline of Final Research Achievements |
A statistical aspect of a quantity called the odds ratio was investigated. The odds ratio is a quantity obtained by taking the ratio of two odds. The odds is an index of the likelihood (probability) of an event occurring. In this study, for example, we considered probability distributions called matching priors in Bayesian statistics for odds ratios. We also proposed a statistical sparse estimation method using the fact that the odds ratio is a parameter called a natural parameter. The method’s performance was evaluated through numerical experiments.
|
| Academic Significance and Societal Importance of the Research Achievements |
オッズ比は統計学の理論においても実用においても重要な量である．また，ある問題設定でオッズ比を含む自然パラメータと呼ばれるパラメータも，理論と応用の両面で頻繁に利用される．本課題では，統計学の問題として分割表や回帰，時系列などを想定し，これらのパラメータの推定を考察することにより，推定問題の性質の調査や，それを活かした推定方法を提案したという点で学術的意義がある．また，応用分野（物理化学）への推定の適用にも取り組んだ点にも学術的意義がある．
|
