Randomized experiments provide policy relevant treatment effects if there are no spillovers between participants and nonparticipants. We show that this assumption is violated for a Danish activation program for unemployed workers. Using a difference-in-difference model we show that the...

When treatment effects of active labour market programmes are heterogeneous in an observable way across the population, the allocation of the unemployed into different programmes becomes a particularly important issue. In this paper, we present a statistical model designed to improve the present...

This paper compares the effectiveness of public and private providers of employment services. Reporting from a randomized field experiment conducted in Denmark we assess empirically the case for contracting out employment services for a well-defined group of highly educated job-seekers...