Abstract
We use information in higher-order moments to identify aggregate supply and aggregate
demand shocks for the U.S. economy. Traditional methods based on sign restrictions and/or
second-order moments yield only “set” or “interval” identification but higher-order moments
are shown to considerably aid identification. Aggregate supply shocks dominated recessions
in the 1970s and early 1980s, while aggregate demand shocks dominated most later recessions.
The Great Recession of 2008-2009 and the pandemic-induced recession of 2020 exhibited both
large negative aggregate demand and large negative aggregate supply shocks.