Predicting U.S. Business Cycle Turning Points Using Real-Time Diffusion Indexes Based on a Large Data Set
29 Pages Posted: 20 Sep 2016
Date Written: September 16, 2016
This paper considers the issue of predicting cyclical turning points using real-time diffusion indexes constructed using a large data set from March 2005 to September 2014. We construct diffusion indexes at the monthly frequency, compare several smoothing and signal extraction methods, and evaluate predictions based on the indexes. Our finding suggest that diffusion indexes are still effective tools in predicting turning points. Using diffusion indexes, along with good judgement, one would have successfully predicted or at least identified the 2008 recession in real time.
Keywords: forecasting recession, real-time data, probability forecast
JEL Classification: C43, C53, C55, E37
Suggested Citation: Suggested Citation