Detecting Time-dependent Bias in the Fed's Greenbook Forecasts of Foreign GDP Growth

• Activity Number: 23
• Type: Topic Contributed
• Date/Time: Sunday, August 9, 2015 : 2:00 PM to 3:50 PM
• Sponsor: Business and Economic Statistics Section
• Author(s): Neil R. Ericsson* and Emilio J. Fiallos and J. E. Seymour
• Companies: Federal Reserve Board and Rutgers University and Federal Reserve Board
• Keywords: Autometrics ; bias ; Federal Reserve ; GDP ; Greenbook ; Impulse indicator saturation

Abstract

Building on Sinclair, Joutz, and Stekler (2010) and Ericsson, Hood, Joutz, Sinclair, and Stekler (2013), this paper examines publicly available Fed Greenbook forecasts of several foreign countries' GDP growth, focusing on potential biases in the forecasts. While standard tests typically fail to detect biases, recently developed indicator saturation techniques detect economically sizable and highly significant time-varying biases. Estimated biases differ not only over time, but by country and across the forecast horizon.