Nonparametric identification of unobserved technological heterogeneity in production

We propose a novel nonparametric method for the structural identification of unobserved technological heterogeneity in production. We assume cost minimization as the firms' behavioral objective, and we model unobserved heterogeneity as an unobserved productivity factor on which firms condition the input demand of the observed inputs. Our model of unobserved technological differences can equivalently be represented in terms of unobserved\latent capital" that guarantees data consistency with our behavioral assumption, and we argue that this avoids a simultaneity bias in a natural way. Our empirical application to Belgian manufacturing data shows that our method allows for drawing strong and robust conclusions, despite its nonparametric orientation. For example, our results pinpoint a clear link between international exposure and technological heterogeneity and show that primary inputs are in the considered sectors substituted for materials rather than for technology.