Forecasting extreme risk using regime-switching GARCH models: a case from an energy commodity

Abstract

Purpose

The purpose of this paper is to investigate regime-switching and single-regime GARCH models for the extreme risk forecast of the developed and the emerging crude oil markets.

Design/methodology/approach

The regime-switching GARCH-type models and their single-regime counterparts are used in risk forecast of crude oil.

Findings

The author finds that the regime-switching GARCH-type models are suitable for the developed and the emerging crude oil markets in that they effectively measure the extreme risk of crude oil in different cases. Meanwhile, the model with switching regimes captures dynamic structures in financial markets, and these models are just only better than the corresponding single-regime in terms of long position risk forecast, instead of short position. That is, it just outperforms the single-regime on the downside risk forecast.

Originality/value

This study comprehensively compares risk forecast of crude oil in different situations through the competitive models. The obtained findings have strong implications to investors and policymakers for selecting a suitable model to forecast extreme risk of crude oil when they are faced with portfolio selection, asset allocation and risk management.

Citation

Xiao, Y. (2021), "Forecasting extreme risk using regime-switching GARCH models: a case from an energy commodity", International Journal of Emerging Markets, Vol. 16 No. 8, pp. 1556-1582. https://doi.org/10.1108/IJOEM-11-2019-0974