Reverse regression has recently been proposed to assess discrimination by gender or race. We consider several stochastic models and find one that justifies reverse regression. Testable implications are deduced, and the analysis is illustrated with empirical material.

This article considers anew the problem of estimating a regression E(y|x) when realizations of (y, x) are sampled randomly but y is observed selectively. The central issue is the failure of the sampling process to identify E(y|x). The problem faced by the researcher is to find correct prior...

This paper analyzes the probabilistic measures of job insecurity that have recently become available through the nationwide Survey of Economic Expectations (SEE). Since 1994, employed SEE respondents have been asked questions eliciting their subjective probabilities of job loss in the coming...

We report here on the design and first application of an interactive computer-assisted self-administered interview (CASI) survey eliciting from high school students and college undergraduates their expectations of the income they would earn if they were to complete different levels of schooling....

The importance of social programs to a diverse population creates a legitimate concern that the findings of evaluations be widely credible. The weaker the assumptions imposed, the more widely credible are the findings. The classical argument for random assignment of treatments is viewed by many...

The effects of tuition costs, financial aid, and individual attributes on college choice are analyzed using a conditional logit model. The results confirm that financial aid can be an important determinant of postsecondary school attendance and that individual academic ability relative to the...