Oil Shocks and Stock Return Volatility

Abstract

Asset return volatility is important to the macroeconomy. This paper asks whether oil price volatility can be used as a predictor of stock return volatility. In contrast with previous research, we focus on the out-of-sample predictive power of oil price volatility rather than on in-sample inference. Formal tests of out-of-sample predictive ability find no evidence supporting the use of oil price volatility as a predictor of future stock return volatility. Further analysis using rolling window estimation and structural break tests shows that the coefficients of this relationship are very unstable. The coefficients can be positive, negative, or close to zero depending on the sample that is chosen. We discuss the implications of this finding for monetary policy.