This paper investigates the role of macroeconomic and financial uncertainty in forecasting recessions in the United States. The analysis uses a probit model that also includes other predictors besides the uncertainty variables, such as the slope of the yield curve, on US data from 1972-2018.
In-sample forecasts show that macroeconomic and financial uncertainty are the best predictors of recessions in the short run; in the longer run, macro uncertainty is the second best predictor, just after the yield curve slope. Out-of-sample forecasts shows that uncertainty contributed significantly to lowering the probability of a recession in 2019, which indeed did not occur.
Published in 2020 in: Economics Letters, v. 193
