An evaluation of the predictions of the Federal Reserve

To successfully implement monetary policy, the Federal Reserve System (FED) must make forecasts about the future state of the economy. This paper examines some of the characteristics of these forecasts. The analysis presents the usual error measures and tests for rationality. The paper compares these predictions with those generated by ARIMA models and the ASA/NBER surveys. In addition, we analyze (1) the relationship between accuracy and the length of the forecast horizon, (2) whether accuracy has improved over time, and (3) the accuracy of the forecasts in the vicinity of turning points. We conclude that the FED predictions tended to yield the same type of errors that private forecasters have displayed: in some periods either real GNP or inflation had systematic errors; turning point errors occurred prior to recessions; the forecasts were unbiased, but showed evidence of inefficiency. However, the FED forecasts were not significantly different from the predictions of the ARIMA models or ASA/NBER surveys.