| Budget Amount *help |
¥2,340,000 (Direct Cost: ¥1,800,000、Indirect Cost: ¥540,000)
Fiscal Year 2014: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2013: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2012: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
|
|---|
| Outline of Final Research Achievements |
This study investigates the test performance of new methods of testing for unit roots or cointegration in nonstationary panels. The study extends these tests to deal with data with structural breaks or nonlinearity. It also applies them, in their original or extended forms, to actual data. I use Romano and Wolf’s (2005) multiple testing based on the bootstrap method and observe the following three noteworthy points in the results: (1) The test can avoid the multiplicity problem (over-rejection of the null hypothesis caused by the repeated use of a single test) and increase test power, while other multiple testing methods suffer from a lack of power. (2) The test can be easily extended to consider cases where structural breaks or nonlinearity is observed in the data; it exhibits good test performance even in these cases. (3) The obtained empirical results are meaningful when some tests are applied to actual exchange rates or financial data.
|
