File(s) under permanent embargo
Localized level crossing random walk test robust to the presence of structural breaks
journal contribution
posted on 2023-05-17, 05:20 authored by Alexeev, V, Maynard, AA modified version of the nonparametric level crossing random walk test is proposed, in which the crossing level is determined locally. This modification results in a test that is robust to unknown multiple structural breaks in the level and slope of the trend function under both the null and alternative hypotheses. No knowledge regarding the number or timing of the breaks is required. An algorithm is proposed to select the degree of localization in order to maximize bootstrapped power in a proximate model. A computational procedure is then developed to adjust the critical values for the effect of this selection procedure by replicating it under the null hypothesis. The test is applied to Canadian nominal inflation and nominal interest rate series with implications for the Fisher hypothesis.
History
Publication title
Computational Statistics and Data AnalysisVolume
56Issue
11Pagination
3322-3344ISSN
0167-9473Department/School
TSBEPublisher
Elsevier Science BvPlace of publication
Po Box 211, Amsterdam, Netherlands, 1000 AeRights statement
The definitive version is available at http://www.sciencedirect.comRepository Status
- Restricted