In 2001, the Swedish system of student aid for college students was substantially reformed; the grant-share of the total aid was increased, students were allowed to earn more without a reduction in student aid, and the repayment schedule of the loans was significantly tightened. In this paper, we...

In 2001, the Swedish system of student aid for college students was substantially reformed; the grant-share of the total aid was increased, students were allowed to earn more without a reduction in student aid, and the repayment schedule of the loans was significantly tightened. In this paper, we...

In many cases assignment to a treatment may affect concomitant variables. I show how a concomitant variable can be used to corroborate evidence from an observational study. In the observational study two types of training programs are compared. One program is part of regular Swedish labor market...

In this paper we perform inference on the effect of a treatment on survival times in studies where the treatment assignment is not randomized and the assignment time is not known in advance. Two such studies are discussed: a heart transplant program and a study of Swedish unemployed eligible for...

The identification of average causal effects of a treatment in observational studies is typically based either on the unconfoundedness assumption or on the availability of an instrument. When available, instruments may also be used to test for the unconfoundedness assumption (exogeneity of the...

The identification of average causal effects of a treatment in observational studies is typically based either on the unconfoundedness assumption or on the availability of an instrument. When available, instruments may also be used to test for the unconfoundedness assumption (exogeneity of the...