Gupta, RanganKanda, PatrickTiwari, Aviral KumarWohar, Mark E.2020-03-062019-11Gupta, R., Kanda, P., Tiwari, A.K. et al. 2019, 'Time-varying predictability of oil market movements over a century of data : the role of US financial stress', The North American Journal of Economics and Finance, vol. 50, art. 100994, pp. 1-11.1062-9408 (print)1879-0860 (online)10.1016/j.najef.2019.100994http://hdl.handle.net/2263/73652In this paper we analyze whether a news-based measure of financial stress index (FSI) in the US can predict West Texas Intermediate oil returns and (realized) volatility over the monthly period of 1889:01 to 2016:12, using a dynamic conditional correlation multivariate generalized autoregressive conditional heteroscedasticity (DCC-MGARCH) model. Our results show that, standard linear Granger causality test fail to detect any evidence of predictability. However, the linear model is found to be misspecified due to structural breaks and nonlinearity, and hence, the result of no causality from FSI to oil returns and volatility cannot be considered reliable. When we use the DCC-MGARCH model, which is robust to such misspecifications, in 75 percent and 80 percent of the sample periods, FSI in fact do strongly predict the oil returns and volatility respectively. Overall, our results highlight that FSI is helpful in predicting oil returns and volatility, when one accounts for nonlinearity and regime changes through a robust time-varying model.en© 2019 Elsevier Inc. All rights reserved. Notice : this is the author’s version of a work that was accepted for publication in North American Journal of Economics and Finance. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. A definitive version was subsequently published in North American Journal of Economics and Finance, vol. 50, art. 100994, pp. 1-11, 2019. doi : 10.1016/j.najef.2019.100994.Financial stress index (FSI)Dynamic conditional correlation multivariate generalized autoregressive conditional heteroscedasticity (DCC-MGARCH)US financial stress indexUnited States (US)WTI oil returnsRealized volatilityWest Texas intermediate (WTI)Postprint Article