We provide simple tests for selection on unobserved variables in the Vytlacil-Imbens-Angrist framework for Local Average Treatment Effects. The tests allow researchers not only to test for selection on either or both of the treated and untreated outcomes, but also to assess the magnitude of the...

This paper introduces a new measure of dependence or jointness among explanatory variables. Jointness is based on the joint posterior distribution of variables over the model space, thereby taking model uncertainty into account. By looking beyond marginal measures of variable importance,...

A wide class of models with On-the-Job Search (OJS) predicts that workers gradually select into better-paying jobs. We develop a simple methodology to test predictions implied by OJS using two sources of identification: (i) time-variation in job-finding rates and (ii) the time since the last...

This study estimates the effect of compulsory schooling on earnings. For identification, I exploit a German reform that extended the duration of secondary schooling in the 1960s. I find that hourly wages increase by 6%-8% per additional year of schooling. This result challenges prior findings...

Expanded international data from the PIAAC survey of adult skills allow us to analyze potential sources of the cross-country variation of comparably estimated labor-market returns to skills in a more diverse set of 32 countries. Returns to skills are systematically larger in countries that have...

Students' choices in education can only be based on expected outcomes. Econometric models that infer expectations based on ex post outcomes impose a rational structure of expectations on school performance and post-graduation earnings. Direct surveys suggest much ignorance and fuzziness. We use...

This paper estimates the effect of graduating from college on lifetime earnings. Motivated by the fact that nearly half of all college students fail to earn a bachelor's degree, we study a model of risky college completion. The central idea is that students drop out of college mainly because...

Existing estimates of the labor-market returns to human capital give a distorted picture of the role of skills across different economies. International comparisons of earnings analyses rely almost exclusively on school attainment measures of human capital, and evidence incorporating direct...

How important is mastering information and communication technology (ICT) in modern labor markets? We answer this question with unique data on ICT skills tested in 19 countries. Our two instrumental-variable models exploit technologically induced variation in broadband Internet availability that...