This paper proposes a simple explanation for the frequent appearance of a price puzzle in VARs designed for monetary policy analysis. It suggests that the best method of solving the puzzle implies a close connection between theory and empirics rather than the introduction of a commodity price. It proves that the omission of a measure of output gap (or potential output) spuriously produces a price puzzle in a wide class of commonly used models. This can happen even if the model admits a triangular identification and if the forecasts produced by the misspecified VAR are optimal. In the framework of a model due to Svensson, the omission of a measure of output gap is shown to generate several other incorrect conclusions. When the model is tested on US data, all predictions are supported.
VAR monetary policy misspecification output gap technology shocks.