Keywords
asymmetric effects, dynamic conditional correlations, multivariate garch models, forward prices and returns, spot prices and returns
Start Date
1-7-2004 12:00 AM
Abstract
This paper estimates the dynamic conditional correlations in the returns on Tapis oil spot and onemonthforward prices for the period 2 June 1992 to 16 January 2004, using recently developed multivariateconditional volatility models, namely the Constant Conditional Correlation Multivariate GARCH (CCCMGARCH)model of Bollerslev [1990], Vector Autoregressive Moving Average – GARCH (VARMAGARCH)model of Ling and McAleer [2003], VARMA – Asymmetric GARCH (VARMA-AGARCH) modelof Chan et al. [2002], and the Dynamic Conditional Correlation (DCC) model of Engle [2002]. Themultivariate estimates show that the ARCH and GARCH effects for spot (forward) returns are significant inthe conditional volatility model for spot (forward) returns. Moreover, there are significant interdependencesin the conditional volatilities between the spot and forward markets. The multivariate asymmetric effects aresignificant for both spot and forward returns. The calculated constant conditional correlations between theconditional volatilities of spot and forward returns using CCC-GARCH(1,1), VAR(1)-GARCH(1,1) andVAR(1)-AGARCH(1,1) are virtually identical. Finally, the estimates of the two DCC parameters arestatistically significant, which makes it clear that the assumption of constant conditional correlation is notsupported empirically.
Modelling Dynamic Conditional Correlations in the Volatility of Spot and Forward Oil Price Returns
This paper estimates the dynamic conditional correlations in the returns on Tapis oil spot and onemonthforward prices for the period 2 June 1992 to 16 January 2004, using recently developed multivariateconditional volatility models, namely the Constant Conditional Correlation Multivariate GARCH (CCCMGARCH)model of Bollerslev [1990], Vector Autoregressive Moving Average – GARCH (VARMAGARCH)model of Ling and McAleer [2003], VARMA – Asymmetric GARCH (VARMA-AGARCH) modelof Chan et al. [2002], and the Dynamic Conditional Correlation (DCC) model of Engle [2002]. Themultivariate estimates show that the ARCH and GARCH effects for spot (forward) returns are significant inthe conditional volatility model for spot (forward) returns. Moreover, there are significant interdependencesin the conditional volatilities between the spot and forward markets. The multivariate asymmetric effects aresignificant for both spot and forward returns. The calculated constant conditional correlations between theconditional volatilities of spot and forward returns using CCC-GARCH(1,1), VAR(1)-GARCH(1,1) andVAR(1)-AGARCH(1,1) are virtually identical. Finally, the estimates of the two DCC parameters arestatistically significant, which makes it clear that the assumption of constant conditional correlation is notsupported empirically.
