Examining the market linkage between the US stock market and the oil market: A multivariate GARCH approach

Abstract: In this study the relationship between the US stock market and the oil market is examined in terms of volatility and co-volatility. A multivariateGARCH approach is therefore applied by using an asymmetric BEKK model on daily returns which cover the period from 1 January 2002 to 31 December 2008. The linkage between the markets is further explored with the creation of news impact surfaces for the conditional variances, covariance and correlation. Empirical evidence of volatility spillover from the US stock market to the oil market is found. This suggests that information has altered the expectations of the US investors which has led to changes in hedging demand and through cross-market hedging volatility is spilled over to the oil market. Alternatively the volatility spillover is caused by market dynamics which means that the oil market’s speed of adjustment to US news is not efficient while the US stock market efficiently incorporates all oil news. The news impact surface for the oil market’s conditional variance shows that the effect of volatility spillover is large but the oil market’s own shocks have the largest effect. Furthermore, the news impact surface for the conditional covariance shows that the shift in sign in the covariance is related to the signs of the shocks. There is generally positive covariance when both shocks are of the same sign and otherwise negative covariance.