Using only aggregate data as observables, we estimate multisector sticky-price models for twelve countries, allowing the degree of price stickiness to vary across sectors. We use a specification that allows us to extract information about the underlying cross-sectional distribution from aggregate data. Identification is possible because sectors play different roles in determining the response of aggregate variables to shocks at different frequencies: sectors where prices are more sticky are relatively more important in determining the low-frequency response. We find that the inferred distributions of price stickiness conform quite well with empirical distributions constructed from the available microeconomic evidence on price setting. We then explore our Bayesian approach to combine the aggregate time-series data with the microeconomic information on the distributions of price rigidity, and re-estimate the models for the United States, Denmark, and Japan. Our results show that allowing for this type of heterogeneity is critically important to understanding the joint dynamics of output and prices, and it constitutes a step toward reconciling the extent of nominal price rigidity implied by aggregate data with the evidence from price micro data.
Heterogeneity price stickiness micro data macro data Bayesian estimation