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 use data from a promotion campaign of NH-Hoteles to study self-selection of participants in a gift-exchange experiment. The promotion campaign allowed guests to pay any non negative amount of money for a stay in one of 36 hotels in Belgium and the Netherlands. The data allow us to distinguish...

We investigate the presence of moral hazard and advantageous or adverse selection in a market for supplementary health insurance. For this we specify and estimate dynamic models for health insurance decisions and health care utilization. Estimates of the health care utilization models indicate...

In a non-stationary job search model we allow unemployed workers to have a permanent option to leave the labour force. Transitions into nonparticipation occur when reservation wages drop below the utility of being nonparticipant. Taking account of these transitions allows the identification of...

We investigate the presence of moral hazard and advantageous or adverse selection in a market for supplementary health insurance. For this we specify and estimate dynamic models for health insurance decisions and health care utilization. Estimates of the health care utilization models indicate...

In this article we introduce a test for the normality assumption in the sample selection model. The test is based on a flexible parametric specification of the density function of the error terms in the model. This specification follows a Hermite series with bivariate normality as a special...

We provide evidence from a large-scale field experiment on the causal effects of audit rules on compliance in a market for long-term care. In this setting care should be provided quickly and, therefore, the gatekeeper introduced ex-post auditing. Our results do not show significant effects of...

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...