Ignacio Monzon (Collegio Carlo Alberto)

“Identifying Sorting in Practice”

Abstract

We propose a novel methodology to detect assortative matching in the labor market using information on workers’ mobility, firms’ profits, and wages. We estimate the strength of sorting from a ranking of firms alone, built from firm-level profits. We identify the strength of sorting from the fraction of the variance in firm types explained by worker types. In order to discern the sign of sorting, we build a (potentially) noisy ranking of workers from wage data. We provide a consistent test for the sign of sorting despite the noise in worker rankings. Intuitively, we test whether better workers typically move to (or come from) better firms. We use a panel data set that combines
social security earnings records for workers in the Veneto region of Italy with detailed balance-sheet data for firms. We find robust evidence for positive sorting. The correlation between the worker and firm types ranges from 50% to 60%.