Testing for abrupt breaks in variance structures with smooth changes

Raja Ben Hajria, Salah Khardani, Hamdi Raïssi

Research output: Contribution to journalReview articlepeer-review

Abstract

We investigate the problem of testing for variance breaks in the case where the variance structure is assumed to be smoothly time-varying under the null. Since the classical tests are aimed to detect any change in the variance, they are not able to distinguish between smooth non constant variance and abrupt breaks. In this paper a new procedure for detecting variance breaks taking into account for smooth changes in the variance under the null is proposed. The finite sample properties of the test we introduce are investigated by Monte Carlo experiments. The theoretical outputs are illustrated using U.S. macroeconomic data.

Original languageEnglish
Pages (from-to)5195-5212
Number of pages18
JournalCommunications in Statistics - Theory and Methods
Volume48
Issue number21
DOIs
StatePublished - 2 Nov 2019
Externally publishedYes

Keywords

  • CUSUM test
  • Unconditionally heteroscedastic errors
  • variance breaks

Fingerprint

Dive into the research topics of 'Testing for abrupt breaks in variance structures with smooth changes'. Together they form a unique fingerprint.

Cite this