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...

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...

On normal days, the temperature decreases with altitude, allowing air pollutants to rise and disperse. During inversion episodes, a warmer air layer at higher altitude traps pollutants close to the ground. We show how readily available NASA satellite data on vertical temperature profiles can be...

Women are on average more absent from work for health reasons than men. At the same time, they live longer. This conflicting pattern suggests that part of the gender difference in health-related absenteeism arises from differences between the genders unrelated to actual health. An overlooked...

This study investigates possible reasons for the gender difference in sickness absence. We estimate both short- and long-term effects of parenthood in a within-couple analysis based on the timing of parenthood. We find that after entering parenthood, women increase their sickness absence by...

We compare the income and wage trajectories of women in relation to their male partners before and after parenthood. Focusing on the within-couple gap allows us to control for both observed and unobserved attributes of the spouse and to estimate both short- and long-term effects of entering...

When a treatment unambiguously defines the treatment and control groups at a given time point, its effects are usually found by comparing the two groups' mean responses. But there are many cases where the treatment timing is chosen, for which the conventional approach fails. This paper sets up...