Bayesian approach to the discrete choice model with multiple selection of alternatives
| Project/Area Number |
15K17041
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Economic statistics
|
|---|
| Research Institution | Kwansei Gakuin University |
|---|
Principal Investigator |
MIYAWAKI Koji 関西学院大学, 経済学部, 准教授 (40550249)
|
|---|
| Project Period (FY) |
2015-04-01 – 2019-03-31
|
| Project Status |
Completed (Fiscal Year 2018)
|
| Budget Amount *help |
¥3,120,000 (Direct Cost: ¥2,400,000、Indirect Cost: ¥720,000)
Fiscal Year 2017: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2016: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2015: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
|
|---|
| Keywords | 経済統計 / 経済統計学 / ベイズ統計学 |
|---|
| Outline of Final Research Achievements |
This project focused on the discrete choice model where the multiple selection of alternatives is allowed. The inference based on the simple statistical model directly derived from the economic theory is vitrually infeasible because of its computational burden. To address this issue, the project generalizes the simple one preserving the relationship with the economic theory, and develops the estimation method for this generalized statistical model. Because the model cannot identify part of model parameters, several solutions are considered. Comparison of them suggests the estimation method with relatively lower computational burden is favorable. The statistical model and its estimation method are applied to the real dataset.
|
| Academic Significance and Societal Importance of the Research Achievements |
個人の行動を分析する場合，離散選択問題はしばしば観察される．また複数選択が可能である状況もある．そのような行動を分析するにあたって，経済理論に基づいた統計的な分析を行うことは限定的な状況でしかなされてこなかった．本研究では，分析枠組みをより一般的な状況に拡張したとともに，推定可能な統計的モデルの構築及びその推定手法の開発を行うことができたと考えている．また推定上の課題がいくつかあるが，それらに対してもより現実的な解を提案できたと考えている．応用例としては，自動車の選択行動の分析が考えられ，本研究の手法を用いれば，例えばガソリン税の効果を分析することが可能であると考えている．
|
Report
(5 results)
Research Products
(3 results)
