The aim of this paper is to analyse the causal link between monthly oil futures price changes and a sub-grouping of S&P 500 stock index changes. The causal linkage between oil and stock markets is modelled using a vector autoregressive model with time-varying parameters so as to reflect changes in Granger causality over time. A Markov switching vector autoregressive (MS-VAR) model, in which causal link between the series is stochastic and governed by an unobservable Markov chain, is used for inferring time-varying causality. Although we do not find any lead-lag type Granger causality, the results based on the MS-VAR model clearly show that oil futures price has strong regime prediction power for a sub-grouping of S&P 500 stock index during various sub-periods in the sample, while there is a weak evidence for the regime prediction power of a sub-grouping of S&P 500 stock indexes. The regime-prediction non-causality tests on the MS-VAR model show that both variables are useful for making inference about the regime process and that the evidence on regime-prediction causality is primarily found in the equation describing a sub-grouping of S&P 500 stock market returns. The evidence from the conditional non-causality tests shows that past information on the other series fails to improve the one step ahead prediction for both oil futures and stock returns. (c) 2013 Elsevier B.V. All rights reserved.