Tests of the Constancy of Conditional Correlations of Unknown Functional Form in Multivariate GARCH Models

Anne Peguin-Feissolle () and Bilel Sanhaji
Additional contact information
Anne Peguin-Feissolle: GREQAM - Groupement de Recherche en Économie Quantitative d'Aix-Marseille - EHESS - École des hautes études en sciences sociales - AMU - Aix Marseille Université - ECM - École Centrale de Marseille - CNRS - Centre National de la Recherche Scientifique

Post-Print from HAL

Abstract: We introduce two tests for the constancy of conditional correlations of unknown functional form in multivariate GARCH models. The first test is based on artificial neural networks and the second on a Taylor expansion of each unknown conditional correlation. They can be seen as general misspecification tests for a large set of multivariate GARCH-type models. We investigate their size and their power through Monte Carlo experiments. Moreover, we study the robustness of these tests to nonnormality by simulating some models, such as the GARCH − t and Beta − t − EGARCH . We give some illustrative empirical examples based on financial data.

Keywords: Multivariate GARCH; Neural Network; Taylor Expansion (search for similar items in EconPapers)
Date: 2016
Note: View the original document on HAL open archive server: https://hal.science/hal-04218472v1
References: Add references at CitEc
Citations: View citations in EconPapers (1)

Published in Annals of Economics and Statistics, 2016, 123/124, pp.77. ⟨10.15609/annaeconstat2009.123-124.0077⟩

Downloads: (external link)
https://hal.science/hal-04218472v1/document (application/pdf)

Related works:
Journal Article: Tests of the Constancy of Conditional Correlations of Unknown Functional Form in Multivariate GARCH Models (2016)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hal:journl:hal-04218472

DOI: 10.15609/annaeconstat2009.123-124.0077

Access Statistics for this paper

More papers in Post-Print from HAL
Bibliographic data for series maintained by CCSD ().