CMStatistics 2021: Start Registration
View Submission - CFE
A1332
Title: Evaluating the federal reserves tealbook forecasts Authors:  Neil Ericsson - Federal Reserve Board (United States) [presenting]
Abstract: Publicly available Federal Reserve Board Tealbook forecasts of GDP growth for the United States and several foreign countries are examined focusing on potential time-varying biases and evaluating the Tealbook forecasts relative to other institutions forecasts. Tealbook forecasts perform relatively well at short horizons, but with significant heterogeneity across countries. Also, while standard Mincer-Zarnowitz tests typically fail to detect biases in the Tealbook forecasts, recently developed indicator saturation techniques that employ machine learning are able to detect economically sizable and highly significant time-varying biases. Estimated biases differ not only over time, but by country and across the forecast horizon. These biases point to directions for forecast improvement. Previous forecast-encompassing tests of the Tealbook forecasts relative to JP Morgan's forecasts reveal distinct value added by each institution's forecasts. However, for most countries and forecast horizons examined, each institution's forecast can be improved by utilizing information from the other institution's forecast.