Volatility forecasting in commodity markets using macro uncertainty

In this paper, we empirically examine the predictive power of macroeconomic uncertainty on the volatility of agricultural, energy and metals commodity markets. We find that the latent macroeconomic uncertainty measure of Jurado et al. (2015) is a common volatility forecasting factor for commodity markets, which provides statistically significant volatility predictions for forecasting horizons up to twelve months ahead. The results indicate that the forecasting power of macroeconomic uncertainty is higher when predicting the volatility of energy commodities. Our findings also show that higher macroeconomic uncertainty is associated with large volatility episodes subsequently observed in all commodity markets. The predictive power of the unobservable macroeconomic uncertainty factor remains robust to the inclusion of observable economic uncertainty measures, historical commodity price volatility, stock-market realized and news implied volatility, oil price shocks and other macroeconomic variables which are closely related to the production process and the mechanics of commodity markets.