Economic statistics should be used with caution. That admonition is not new, as economists have often warned of errors of observation, conceptual ambiguities, and spurious accuracy embedded in economic data

Why are forecasts of inflation from VAR models so much worse than their forecasts of real variables? This paper documents that relatively poor performance, and finds that the price equation of a VAR model fitted to U.S. postwar data is poorly specified. Statistical work by other authors has...

In his article, “Vector Autoregressions as a Tool for Forecast Evaluation,” Roy H. Webb proposes that VAR forecasts be used as a standard of comparison for other forecasts. He begins by explaining how conventional forecasting models are constructed and used, and summarizes a few common...

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.