2009 Fiscal Year Final Research Report
Improving an instrumental variables estimator in dynamic panel data models
| Project/Area Number |
20830056
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (Start-up)
|
| Allocation Type | Single-year Grants |
|---|
| Research Field |
Economic statistics
|
|---|
| Research Institution | Hiroshima University |
|---|
Principal Investigator |
HAYAKAWA Kazuhiko Hiroshima University, 大学院・社会科学研究科, 講師 (00508161)
|
|---|
| Project Period (FY) |
2008 – 2009
|
| Keywords | パネルデータモデル |
|---|
| Research Abstract |
In this project, I tried to compare and improve estimators of dynamic panel data models. Specifically, in a dynamic panel model with an exogenous variable, I investigated the behavior of the GMM estimator in several schemes which depend on how individual effects are removed and the type and number of instruments. Furthermore, related to the assumption of mean-stationarity of data, I discussed how large the improvement is by exploiting the level model which is valid only when data are mean-stationary, and how the GMM estimator behaves when mean-stationarity is violated.
|
