The matching method for treatment evaluation does not balance selective unobserved differences between treated and non-treated. We derive a simple correction term if there is an instrument that shifts the treatment probability to zero in specific cases. Policies with eligibility restrictions,...

The Swedish adult education program known as the Knowledge Lift (1997-2002) was unprecedented in its size and scope, aiming to raise the skill level of large numbers of low-skill workers. This paper evaluates the potential effects of this program on aggregate labor market outcomes. This is done...

We analyze the effect of being born in a recession on the mortality rate later in life in conjunction with social class. We use individual data records from Dutch registers of birth, marriage, and death certificates, covering the period 1815-2000, and we merge these with historical data on...

We survey the recent literature on the effects of active labor market policies on individual labor market outcomes like employment and income, for adult female individuals without work in European countries. We consider skill-training programs, monitoring and sanctions, job search assistance,...

Instrumental variable estimation requires untestable exclusion restrictions. With policy effects on inidividual outcomes, there is typically a time interval between the moment the agent realizes that he may be exposed to the policy and the actual exposure or the announcement of the actual...

Major events in the life of an older individual, such as retirement, a significant decrease in income, death of the spouse, disability, and a move to a nursing home, may affect the mental health status of the individual. For example, the individual may enter a prolonged depression. We...

The Dutch Hunger Winter (1944/45) is the most-studied famine in the literature on long-run effects of malnutrition in utero. Its temporal and spatial dermacations are clear, it was severe, it was anticipated, and nutritional conditions in society were favorable and stable before and after the...

Shared-frailty survival models specify that systematic unobserved determinants of duration outcomes are identical within groups of individuals. We consider random-effects likelihood-based statistical inference if the duration data are subject to left-truncation. Such inference with...