Empirical Comparison of Sticky Price and Sticky Information Models

The goal of this paper is to provide a fair empirical comparison of two alternative explanations of the relationship between aggregate price and output. We compare the empirical performance of the sticky price and the Mankiw and Reis (2002) sticky information models. We put both models in a similar analytical form and use the same data set on unit labor cost and aggregate prices in the U.S. after WWII to evaluate the models. We use the Bayesian full information likelihood approach for parameter estimation, uncertainty evaluation, and model comparison. Statistical comparison of the two non-nested models and estimates of the empirical encompassing model lead to the same result - the sticky information model is dominated by the sticky price model.