Forecasting and nowcasting real GDP: Comparing statistical models and subjective forecasts

We conduct a systematic comparison of the short-term forecasting abilities of eleven statistical models and professional analysts in a pseudo-real time setting, using a large set of monthly indicators. Our analysis covers the euro area and its five largest countries over the years 1996-2011. We find that summarizing the available monthly information in a few factors is a more promising forecasting strategy than averaging a large number of indicator-based forecasts. The dynamic and static factor model outperform other models, especially during the crisis period. Judgmental forecasts by professional analysts often embody valuable information that could be used to enhance forecasts derived from purely mechanical procedures.
 
Keywords: nowcasting, professional forecasters, factor model, judgment, forecasting.
JEL Classification: E52, C53, C33.

Working paper no. 365