Abstract
Copula functions are flexible tools for modelling the dependence structure between variables. In this research, we extend the literature on currency-commodity relationship using copulas. We examine the dependence structure between gold, platinum mineral prices and RAND/USD exchange rate. ARMA (1, 1)-EGARCH (1, 1) and ARMA(1, 1)-APARCH (1, 1) models under different error terms including normal, student-t and skewed student-t were fitted to the returns of commodity prices and the exchange rate. Constants and time varying copulas were then employed to examine the commodity-currency dependence structure. The results show evidence of a positive, strong dependence between gold, platinum prices and the RAND/USD exchange rate. The analysis relies on Clayton, rotated Clayton, Student-t, Gumbel, rotated Gumbel, Plackett and Joe Clayton copulas and provide an indication of leverage effects. The results of the time varying Normal copula indicate that fluctuations in gold and platinum prices generate Rand/USD volatility.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call