October 2020 Adaptive Hyperbolic Asymmetric Power ARCH (A-HY-APARCH) model: Stability and Estimation
Charline UWILINGIYIMANA, Abdou Kâ DIONGUE, Carlos OGOUYANDJOU
Afr. Stat. 15(4): 2511-2528 (October 2020). DOI: 10.16929/as/2020.2511.170

Abstract

In this paper, a new asymmetric GARCH type model that generalizes the Hyperbolic Asymmetric Power ARCH (HY-APARCH) process is proposed. The proposed model takes into consideration some characteristics of financial time series data like volatility clustering, long memory and structural changes. The necessary and sufficient conditions for the asymptotic stability of the model are derived and parameter estimation methods are proposed. The Monte Carlo Simulations are done to prove the performance of the estimation method.

Nous proposons un modèle GARCH symmétrique qui généralise le modèle asymétrique hyperbolique Power ARCH. Notre modèle prend en compte des caractèristiques de séries chronologiques financières telles que la volatilité du grappage, les longues mémoires et les changement structurels. Nous obtenons des conditions nécessaires et suffisantes de statilité asymptotique et procédons à une estimation paramétrique pour valider le modèle. Une étude de simulation vient en appui aux résultats théoriques.

Citation

Download Citation

Charline UWILINGIYIMANA. Abdou Kâ DIONGUE. Carlos OGOUYANDJOU. "Adaptive Hyperbolic Asymmetric Power ARCH (A-HY-APARCH) model: Stability and Estimation." Afr. Stat. 15 (4) 2511 - 2528, October 2020. https://doi.org/10.16929/as/2020.2511.170

Information

Published: October 2020
First available in Project Euclid: 14 January 2021

MathSciNet: MR4199736
Digital Object Identifier: 10.16929/as/2020.2511.170

Subjects:
Primary: 62M10
Secondary: 62F10

Keywords: HYAPARCH , Long range dependence , structural changes

Rights: Copyright © 2020 The Statistics and Probability African Society

JOURNAL ARTICLE
18 PAGES

This article is only available to subscribers.
It is not available for individual sale.
+ SAVE TO MY LIBRARY

Vol.15 • No. 4 • October 2020
Back to Top