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...

We analyze the effects of four randomized social experiments, involving early and intensive active labour market policy, conducted in Denmark in 2008. The experiments entailed different combinations of early and intensive treatment in terms of meetings and active labour market programmes. 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...