Measuring Markups with Revenue Data

Abstract

When output prices are unobserved, standard production-based markup estimators are biased and inconsistent because they are unable to distinguish whether firms have higher revenues due to higher prices or higher quantities. Building on work designed for competitive environments, we propose a novel method that solves this problem using only revenue data. We flexibly model markups as a specified function of observables and fixed effects, supporting a broad class of variable-markup frameworks. We explicitly adopt a Markovian revenue productivity process, a commonly implicit assumption in the literature. Our suggested two-step approach is simple in concept and implementation, requiring only common regression techniques.

Keywords: Markups, Revenue, Omitted Price Bias, Production Functions, Productivity

JEL Classification: C14, C33, D24, D43, L11