2018 Fiscal Year Final Research Report
A study of estimation and inference of the density discontinuity
| Project/Area Number |
17K13713
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Economic statistics
|
|---|
| Research Institution | University of Tsukuba |
|---|
Principal Investigator |
YU Zhengfei 筑波大学, 人文社会系, 助教 (40774758)
|
|---|
| Project Period (FY) |
2017-04-01 – 2019-03-31
|
| Keywords | Density discontinuity / Optimal bandwidth / Empirical likelihood / Manipulation test / Regression discontinuity |
|---|
| Outline of Final Research Achievements |
This research proposes optimal bandwidths for estimating and testing functions of density discontinuity, which can be used to check the validity of the regression discontinuity design, or to estimate agents’ response to the policy change that is related to certain functions of densities around a threshold. For the estimation problem, the proposed method allows different bandwidths on both sides of the threshold, and thus generates more precise estimate for the parameter of interest. For the testing problem, the optimal bandwidth minimizes the coverage error. When applied to the manipulation test for regression discontinuity designs, the proposed method yields the optimal bandwidth with an analytical form, which cannot be obtained by existing methods of density discontinuity inference. Monte Carlo simulations demonstrate advantageous finite sample size and power performances of the proposed methods.
|
| Free Research Field |
計量経済学
|
| Academic Significance and Societal Importance of the Research Achievements |
The proposed optimal bandwidth selectors can be used to improve the performance of testing for the validity of regression discontinuity designs. They can also be used to improve the estimation of structural parameters in economic models related to discontinuous policy changes.
|
