the elite college premium, or my debate with shamus continues
Shamus and I have a long standing debate over the 2002 Dale/Krueger paper and whether it really does show that elite college premia are due to ability bias (e.g., kids who go to Harvard make more money because they are smarter/better connected/whatever, not because Harvard gives them any particular human capital). Via Econlog, I discovered thet D&K have a working paper, which bolsters this claim with newer analysis. From the abstract:
We find that the return to college selectivity is sizeable for both cohorts in regression models that control for variables commonly observed by researchers, such as student high school GPA and SAT scores. However, when we adjust for unobserved student ability by controlling for the average SAT score of the colleges that students applied to, our estimates of the return to college selectivity fall substantially and are generally indistinguishable from zero. There were notable exceptions for certain subgroups. For black and Hispanic students and for students who come from less-educated families (in terms of their parents’ education), the estimates of the return to college selectivity remain large, even in models that adjust for unobserved student characteristics.
In other words, if going to Harvard causes you to get more income, the income associated with going to Harvard should remain unexplained when we control for sensible individual covariates. In the data, when you include data on school you applied to, which indicates how ambitious you are, the Harvard effect goes away, except for low-SES students.
Bottom line: Elite college attendance is a marker of ambition. That’s important to know, but shouldn’t be conflated with a human capital effect, except for populations which don’t have wealth or social connections.