In this paper, we examine whether adult education delays retirement and increases labour force participation among the elderly, a mechanism suggested in the OECD strategy for 'active ageing' and the 'Lisbon strategy' of the EU. Using register data from Sweden, we analyse transcripts from adult...

Training programs for the unemployed typically involve teaching a specific skill to ease the transition into employment. However, in 1997, the Swedish unemployed could choose general/theoretical training through enrollment in one year of full-time studies at the upper secondary school level....

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 observational studies, the non-parametric estimation of a binary treatment effect is often performed by matching each treated individual with a control unit which is similar in observed characteristics (covariates). In practical applications, the reservoir of covariates available may be...

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 study migration and commuting among participants in labour market programmes and individuals in open unemployment. Post-programme mobility of participants in Employment Training, which is a supply-orientated program, is compared to the mobility of individuals participating in two...

Adult education at upper secondary level (AE) is an integral part of the Swedish educational system. Of the cohort born in 1970, about one third has at some point been registered in AE. This evaluation of AE is the first to use register data on the course credits actually attained. The results...

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...

In observational studies, the estimation of a treatment effect on an outcome of interest is often done by controlling on a set of pre-treatment characteristics (covariates). This yields an unbiased estimator of the treatment effect when the assumption of unconfoundedness holds, that is, there...

Truncation or censoring of the response variable in a regression model is a problem in many applications, e.g. when the response is insurance claims or the durations of unemployment spells. We introduce a local polynomial regression estimator which can deal with such truncated or censored...