Analyzing spillover effects of selected cryptocurrencies on gold and brent crude oil under COVID-19 pandemic: Evidence from GJR-GARCH and EVT copula methods

This study examines the dependence structure and estimates the Value at Risk (VaR) and risk spillover between cryptocurrencies, oil, and Gold market data. In this paper, we estimate VaR by applying a hybrid approach of extreme value theory (EVT), copula functions, and GARCH models. We implement this method in a dual pair of selected data: the cryptocurrencies (Bitcoin and Ripple) and the Brent crude oil and gold markets. To estimate the VaR structure of these combinations, we initially employ asymmetric GARCH and EVT methods to model the marginal distributions of each return series and subsequently apply Copula functions (Gaussian, Student's t, Clayton, and Frank) to connect the marginal distributions into a multivariate distribution. Based on the results, we infer that, generally, the GARCH-EVT-Copula approach works well and is better than traditional methods (e. g., Historical Simulation (HS) and variance-covariance (VC)). These results show that the GARCH-EVT-Copula model is the best method for examining the dependence structure. Finally, we implement the technique of Diebold-Yilmaz to compute the spillover index between four data before and during the COVID-19 pandemic. From this part, we conclude that cryptocurrencies have spillovers on each other, but their spillovers on Gold and oil are very small. This phenomenon implies that cryptocurrencies are tough to hedge against other financial assets but are appropriate diversifiers in an investor's portfolio. The current study's findings benefit all investors and financial market professionals who want to learn about the cryptocurrency market as a new asset class or incorporate it into their investment strategies or portfolios.