An <scp>information‐based</scp> index of uncertainty and the predictability of energy prices

We develop an index of uncertainty, the COVID-19 induced uncertainty (CIU) index, and employ it to empirically examine vulnerability energy prices amidst pandemic using a distributed lag model that jointly accounts for conditional heteroscedasticity, autocorrelation, persistence, structural breaks, as well day-of-the-week effect. The nexus between returns is analyzed, daily price eight sources (Brent oil, diesel, gasoline, heating kerosene, natural gas, propane, WTI oil) four news/information-based proxies [CIU, EPU, Global Fear Index (GFI) VIX]. CIU alternative indexes are used, respectively main estimation sensitivity analysis. show outperformance over news in prediction prices. News (aggregate) bad found negatively significantly impact returns, while good has positive impact. Imperatively, variables lack hedging potentials against occasioned by pandemic, we find no strong evidence asymmetry. Our results robust choice variables, forecast horizons employed, with likely