ABSTRACT
This chapter evaluates the accuracy of forecasts of the U.S economy from several perspectives. It examines annual forecasts over the past 35 years to address the questions: On the basis of past experience, how accurate can we expect macroeconomic forecasts to be? and, Has forecast accuracy improved over time? The chapter also examines a richer set of quarterly forecasts over a 12-year period, covering more forecasters, more variables, and multiperiod forecast horizons. These data are used to address the questions of how forecast accuracy differs among variables, across different horizons, and at cyclical turning points. The most obvious conclusion to be drawn from the experience in forecasting the three most recent business cycles is the broad similarity between the performances in the major recessions and the differences between those experiences and the brief 1980 recession. The chapter concludes with remarks on the questions of who is the "best" forecaster and what are the most accurate forecasting techniques.
