Revisiting the relative forecast performances of Fed staff and private forecasters: A dynamic approach

Measuring the Accuracy of Federal Reserve Forecasts

“…For instance, D'Agostino and Whelan () evaluate the mean squared forecast errors of the Fed's Greenbook and Survey of Professional Forecasters’ predictions for growth and inflation in the period since 1991 (up to 2001) and find the Fed's accuracy to have been declined, where their superior forecasting ability applies only to inflation . El‐Shagi et al () expand the Romer and Romer exercise to an even larger sample period (1968–2006) and argue that the presence of large macroeconomic shocks, such as oil price shocks, deteriorates the Fed's forecasting performance. Edge et al () consider the real‐time forecast performance of Federal Reserve staff, time‐series models, and an estimated dynamic stochastic general equilibrium (DSGE) model and present evidence in favor of using a DSGE model instead of forecasts made by Fed staff .…”

Wishful Bias in Predicting US Recessions: Indirect Evidence

“…Third, high UAIs for various target horizons are usually coincident signals of recessions (see Figure 3). 13 Only on the eve of the 1980 recession were there several additional high UAIs; this suggests that serious contractions of GDP were strongly anticipated in 1979. 14 Fourth, none of the three recent recessions (of 1990-91, 2001, and 2008-09) were predicted by the majority of experts; they were only recognized just after the corresponding black swans (the invasion of Kuwait, September 11, and the Lehman Brothers' bankruptcy).…”

Forecast Performance in Times of Terrorism

“…Most notably this literature includes the papers by Giacomini and White (2006), Giacomini and Rossi (2010), and Rossi and Sekhposyan (2016), whose methods we borrow. However, the literature has grown far beyond those original papers, including an abundance of applications such as Barnett et al (2014) and El-Shagi et al (2016), to name just a few.…”