Macroeconomic uncertainty indices based on nowcast and forecast error distributions

The Great Recession of 2007:IV-2009:II sparked great interest in understanding uncertainty and its effects on the macroeconomy. This paper introduces a new approach to measure uncertainty. We start from the same premise as in Jurado et al. (2014), that is: "What matters for economic decision making is whether the economy has become more or less predictable; that is, less or more uncertain." However, as opposed to Jurado et al. (2014), the uncertainty index we propose relies on the unconditional likelihood of the observed outcome. More specifically, our proposed index is the percentile in the historical distribution of forecast errors associated with the realized forecast error.