Research Repository

Refining value-at-risk estimates using a Bayesian Markov-switching GJR-GARCH copula-EVT model

Sampid, Marius and Hasim, Haslifah M and Dai, Hongsheng (2018) 'Refining value-at-risk estimates using a Bayesian Markov-switching GJR-GARCH copula-EVT model.' PLoS ONE, 13 (6). ISSN 1932-6203

journal.pone.0198753.pdf - Published Version
Available under License Creative Commons Attribution.

Download (5MB) | Preview


In this paper, we propose a model for forecasting Value-at-Risk (VaR) using a Bayesian Markov-switching GJR-GARCH(1,1) model with skewed Student’s-t innovation, copula functions and extreme value theory. A Bayesian Markov-switching GJR-GARCH(1,1) model that identifies non-constant volatility over time and allows the GARCH parameters to vary over time following a Markov process, is combined with copula functions and EVT to formulate the Bayesian Markov-switching GJR-GARCH(1,1) copula-EVT VaR model, which is then used to forecast the level of risk on financial asset returns. We further propose a new method for threshold selection in EVT analysis, which we term the hybrid method. Empirical and back-testing results show that the proposed VaR models capture VaR reasonably well in periods of calm and in periods of crisis.

Item Type: Article
Subjects: Q Science > QA Mathematics
Divisions: Faculty of Science and Health > Mathematical Sciences, Department of
Depositing User: Elements
Date Deposited: 13 Sep 2018 14:41
Last Modified: 13 Sep 2018 15:15

Actions (login required)

View Item View Item