2017 Fiscal Year Final Research Report
Generalized empirical likelihood for time series
Project/Area Number |
25870814
|
Research Category |
Grant-in-Aid for Young Scientists (B)
|
Allocation Type | Multi-year Fund |
Research Field |
Statistical science
Economic statistics
|
Research Institution | Waseda University |
Principal Investigator |
|
Project Period (FY) |
2013-04-01 – 2018-03-31
|
Keywords | Empirical Likelihood / Portmanteau Test / GARCH |
Outline of Final Research Achievements |
When we analyze data using time series models, there are many steps such as model selection, estimation of parameters, and diagnostic checking. Generally, since these steps are separately implemented, time series data analysis is complicated. Also, interpretation is difficult when the results of these steps are different. Therefore, we propose empirical likelihood methods that can compute these simultaneously, and elucidated that it has excellent properties especially in diagnostic checking. Simulation studies also showed that the proposed method performed equally or better than the usual method in many cases.
|
Free Research Field |
Time Series Analysis
|