Training programs for the unemployed typically involve teaching specific skills in demand amongst employers. In 1997, Swedish unemployed could also choose general training at the upper secondary school level. Despite the dominance of programs offering specific training, long-term relative...

Most OECD countries experience high unemployment rates and declining growth in higher educational attainment. An often suggested government policy is therefore to allocate resources towards formal schooling for adults. However, returns on such investments are uncertain and the foregone earnings...

Training programs for the unemployed typically involve teaching specific skills in demand amongst employers. In 1997, Swedish unemployed could also choose general training at the upper secondary school level. Despite the dominance of programs offering specific training, long-term relative...

Proxy variables are often used in linear regression models with the aim of removing potential confounding bias. In this paper we formalise proxy variables within the potential outcome framework, giving conditions under which it can be shown that causal effects are nonparametrically identified....

Abadie and Imbens (2008, Econometrica) showed that classical bootstrap schemes fail to provide correct inference for K-nearest neighbour (KNN) matching estimators of average causal effects. This is an interesting result showing that bootstrap should not be applied without theoretical...

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...

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...

Abadie and Imbens (2008, Econometrica) showed that classical bootstrap schemes fail to provide correct inference for K-nearest neighbour (KNN) matching estimators of average causal effects. This is an interesting result showing that bootstrap should not be applied without theoretical...

Evaluations of adults in formal education (AE) are typically based on earnings measured 5-10 years after program enrollment. This paper estimates returns up to 24 years after enrollment, and explore results for 15 cohorts of first-time registered in AE in Sweden 1994-2008 with at least a 10-year...

This paper estimates family spillovers in high school major choice in Sweden, where admission to oversubscribed majors is determined based on GPA. Using a regression discontinuity design, we find large sibling and intergenerational spillovers that depend on the gender mix of a dyad. Same-gender...