Parameter change tests for ARMA–GARCH models

Junmo Song, Jiwon Kang

Research output: Contribution to journalArticlepeer-review

14 Scopus citations

Abstract

This paper considers the problem of testing for parameter change in ARMA–GARCH models. For this, we propose score test and residual-based cumulative sum (CUSUM) test and derive their limiting null distributions. According to our simulation study, the score test performs reasonably in testing for both ARMA and GARCH parameter change, but the residual-based CUSUM test is observed to be unsuitable for detecting changes in parameters belonging to ARMA part. The residual-based CUSUM test, however, outperforms the score test in testing for GARCH parameter change. A real data analysis is provided to illustrate the use of the proposed tests.

Original languageEnglish
Pages (from-to)41-56
Number of pages16
JournalComputational Statistics and Data Analysis
Volume121
DOIs
StatePublished - May 2018

Keywords

  • ARMA–GARCH models
  • Parameter change test
  • Residual-based CUSUM test
  • Score test

Fingerprint

Dive into the research topics of 'Parameter change tests for ARMA–GARCH models'. Together they form a unique fingerprint.

Cite this