The relationship between oil prices, gold prices and US stock market; a time varying investigation

Abstract

The purpose of this research is to investigate the long-run and short-run relationship between oil prices and stock prices in the US economy over the period 01/01/1992 to 07/05/2010. For this purpose four aggregate and twelve sector indices has been examined. The Johansen cointegration method is employed and the cointegrating vectors are estimated using two different estimation techniques: Maximum Likelihood Estimation (MLE) and Dynamic Ordinary Least Squares (DOLS). Moreover, as this investigation focuses on the possible time variation, estimations are conducted using both full sample and rolling sample. The results of the cointegration analysis and the impulse responses imply the existence of a positive relation between oil prices and companies engaged in the oil related sectors. The econometric approach used suggests that gold prices should be taken into consideration and also there are findings that a negative relationship between gold prices and stock prices exists.