2016 Fiscal Year Final Research Report
Improved Over-identifying restriction test in GMM with many moment conditions
| Project/Area Number |
25780153
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Economic statistics
|
|---|
| Research Institution | Hiroshima University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2013-04-01 – 2017-03-31
|
| Keywords | 一般化モーメント法 / 過剰識別検定 / パネルデータ / 共分散構造分析 |
|---|
| Outline of Final Research Achievements |
In this project, I discussed how to improve the performance of the over-identifying restriction test in GMM when many moment conditions are available. Two new approaches are proposed. The first is to use a block diagonal weighting matrix, and the second is to use the principal components of the optimal weighting matrix. Using these two alternative weighting matrices, I proposed two new tests, and derived their asymptotic properties. I carried out Monte Carlo simulation in the context of dynamic panel data models and it is found that the test with a block diagonal weighting matrix is more powerful than that based on the principal components of the optimal weighting matrix.
|
| Free Research Field |
計量経済学
|
