Score contribution per author:
α: calibrated so average coauthorship-adjusted count equals average raw count
We evaluate the forecasting ability of several popular measures of uncertainty. We construct new real‐time versions of both macro‐economic and financial uncertainty, and analyze them together with their ex post counterparts. We find some explanatory power in all uncertainty measures, with relatively good performance by ex post macro‐economic and financial uncertainty. However, real‐time versions perform only about as well as other uncertainty measures such as economic policy uncertainty (EPU), a finding we relate to data revisions in the construction of ex post uncertainty. Real‐time data and estimation considerations are highly consequential, owing to look‐ahead bias. Real‐time uncertainty forecasts real‐time outcome variables better than it forecasts ex post revised outcome variables.