An R-vine copula analysis of non-ferrous metal futures with application in Value-at-Risk forecasting

Abstract

We employ the R-vine copula approach to study the dependence structure between non-ferrous metal commodity futures on the London Metal Exchange, focusing on the comparison before and after structural breaks. We find that the center of the dependence structure between non-ferrous metal futures shifts from copper to zinc after the first structural break in 2008 and moves back to copper after the second structural break in 2014. Additionally, we document that non-ferrous metals experienced an increase in the level of integration and tail dependence between 2008 and 2014, while this increase is shown to cease after 2014. We further develop an R-vine copula-based method for forecasting Value-at-Risk, and the backtesting results show superior forecasting accuracy over the benchmark methods. Our study is useful for market participants seeking to enhance their risk management for non-ferrous metals.