Modeling the Volatility of Returns on Commodities: An Application and Empirical Comparison of GARCH and SV Models

Seven GARCH and stochastic volatility (SV) models are used to model and compare empirically the volatility of returns on four commodities: gold, copper, oil, and natural gas. The results show evidence of fat tails and random jumps created by supply/demand imbalances, international instability episodes, geopolitical tensions, and market speculation, among other factors. We also find evidence of a leverage effect in oil and copper, resulting from their dependence on world economic activity; and of an inverse leverage effect in gold and natural gas, consistent with the former’s role as safe asset and with uncertainty about the latter’s future supply. Additionally, in most cases there is no evidence of an impact of volatility on the mean. Finally, we find that the best-performing return volatility models are GARCH-t for gold, SV-t for copper and oil, and SV with leverage effects (SV-L) for natural gas.

Keywords

Bayesian Estimation, Commodities, Fat Tails, GARCH, Jumps, Leverage, Returns, Stochastic Volatility, Volatility

JEL Classification

C11, C52, G15