We develop estimation methods that use the amount of selection on the observables in a model as a guide to the amount of selection on the unobservables. We show that if the observed variables are a random subset of a large number of factors that influence the endogenous variable and the outcome...

Several previous studies have relied on religious affiliation and the proximity to Catholic schools as exogenous sources of variation for identifying the effect of Catholic schooling on a wide variety of outcomes. Using three separate approaches, we examine the validity of these instrumental...

We develop a framework that may be used to determine the degree to which a school choice program may harm public school stayers by luring the best students to other schools. This framework results in a simple formula showing that the "cream-skimming" effect is increasing in the degree of...

We use linked birth and education records from Florida to investigate how the identification of childhood disabilities varies by race and school racial composition. Using a series of decompositions, we find that black and Hispanic students are identified with disabilities at lower rates than are...

We use rich administrative data from Denmark to assess medical theories that autism spectrum disorder (ASD) is a heritable condition transmitted through underlying parental skills. Positing that occupational choices reflect skills, we create two separate occupation-based skill measures and find...

This paper studies the effect of the change in occupational structure on wages for low skilled men. We develop a model of occupational choice in which workers have multi-dimensional skills that are exploited differently across different occupations. We allow for a rich specification of...

In this paper, we investigate the responsiveness of the demand for college to changes in student aid arising from a Danish reform. We separately identify the effect of aid from that of other observed and unobserved variables such as parental income. We exploit the combination of a kinked aid...

This paper has two main parts. In the first, we describe a method that smooths the objective function in a general class of indirect inference models. Our smoothing procedure makes use of importance sampling weights in estimation of the auxiliary model on simulated data. The importance sampling...

We develop and estimate a life-cycle model in which individuals make decisions about consumption, human capital investment, and labor supply and use it to analyze changes in Social Security rules. The most important aspect of our paper is human capital towards the end of the life cycle which...

There is much public discussion but almost no evidence on the effects of high school curriculum on postsecondary education and on success in the labor market. I use the large variation in curriculum across US high schools to identify the effects on wages and educational attainment of specific...