Unobserved Heterogeneity in the Productivity Distribution and Gains From Trade

A correct parametric approximation of the productivity distribution is essential to calculate Gains From Trade (GFT) in heterogeneous firms models. This paper argues that heterogeneity in productivity is best captured by Finite Mixture Models (FMMs). FMMs build on the existence of unobserved subpopulations in the data. As such, they are generally consistent with models of firm dynamics differing between groups of firms and allow for a very flexible distribution fit. We find FMMs to increase this fit by more than 70% compared to currently considered distributions. A GFT exercise with Portuguese data reveals that only FMMs approximate the ‘true gains’ reasonably well.