Macroeconomic forecasts are traditionally stated as point estimates. Retrospective evaluations of forecasts usually assume that the cost of a forecast error increases with the arithmetic magnitude of the error. As a result, measures such as the root-mean-square error (RSME) or the mean absolute...

Thirty years ago it appeared that the best strategy for improving economic forecasts was to build bigger, more detailed models. As the costs of computing plummeted, considerable detail was added to models and more elaborate statistical techniques became feasible.

In several recent articles, authors have regressed actual values of macroeconomic aggregates on predicted values and claimed that they were testing the rationality of expectations. This paper interprets those regressions as testing a joint hypothesis of imperfect information and rational...