In this paper we derive nonparametric bounds for the cumulative incidence curve within a competing risks model with partly identified interval data. As an advantage over earlier attempts our approach also gives valid results in case of dependent competing risks. We apply our framework to empirically evaluate the effect of unemployment benefits on observed migration of unemployed workers in Germany. Our findings weakly indicate that reducing the entitlement length for unemployment benefits increases migration among high-skilled individuals.


Arntz, Melanie
Lo, Simon M. S.
Wilke, Ralf


cumulative incidence curve, partially missing data, bounds analysis, difference-in-difference