We estimate means and distributions of ex-ante treatment effects for obtaining university education relative to high school. To achieve this, we conducted a survey which elicited earnings expectations associated with counterfactual educational choices for a sample of highschool students in...

This paper exploits a government initiative to analyze the effect of cognitive behavioral therapy (CBT) for individuals with mild or moderate mental illness and multidisciplinary treatment (MDT) for individuals with pain in back and shoulders. We employ a propensity score matching approach to...

This study tests for forward-looking moral hazard in the social insurance system by exploiting a 1991 reform in Sweden. The replacement rate was reduced for short absences but not for long absences, which introduced a potential future cost of returning to work. Using this exogenous variation in...

We provide a framework for the estimation of the impact of fertility timing on female long-term labor supply, measured as labor market work duration. We show that the genuine treatment is waiting time to birth rather than birth per se. In the application we control for the joint decision of...

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....

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...

The issue considered in this study is whether objective, official reports on disability status are reliable. While there is a rather large literature on the reliability of self-reported disability, evidence regarding objective data is scant. It seems to be a widely held view among researchers...

The paper exploits a unique social experiment carried out in 1988 in Sweden to identify the effect of monitoring on sickness absence. The treatment consists of postponing the first formal point of monitoring during a sickness absence spell, a requirement for a doctor’s certificate, from day...

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. We estimate survival functions on a treated and a control group which are made comparable through matching on observed...

We utilize a large-scale randomized social experiment to identify how coworkers affect each other's effort as measured by work absence. The experiment altered the work absence incentives for half of all employees living in Göteborg, Sweden. Using administrative data we are able to recover the...