This paper examines how assumptions imposed on the data influence estimates of schooling's effect on earnings. The paper models schooling decisions as treatment effects and imposes assumptions about schooling selection to estimate bounds on the treatment effect. The study begins by using the worst-case bounds derived by Manski (1989, 1990, 1994, 1995) and adds assumptions from the Roy model of schooling self-selection to narrow the bounds on the schooling treatment effect. The bounds are narrowed further by using family structure, college proximity, and school-quality characteristics as exclusion restrictions. The selection problem requires the researcher to make explicit assumptions to estimate the effect of schooling on earnings. This paper demonstrates that different selection assumptions yield very different results.

In their annual review of academic salaries, the American Association of University Professors observes large gender-related salary differentials. At doctoral-level institutions, male professors at the rank of full professor earn 11.4% more than women full professors. Data on academic labor markets from the Survey of Doctorate Recipients to evaluate gender differences in salaries and promotion probabilities. Differences in employment outcomes by gender are found using two methods: the Oaxaca decomposition is used to examine salary differentials, and duration analysis is used to estimate promotion to tenure. While gender salary differences can largely be explained by academic rank, substantial gender differences in promotion to tenure exist after controlling for productivity, demographic characteristics, and primary work activity.

Can Mentoring Help Female Assistant Professors? Interim Results from a Randomized Trial by Francine D. Blau, Janet M. Currie, Rachel T. A. Croson and Donna K. Ginther. Published in volume 100, issue 2, pages 348-52 of American Economic Review, May 2010