There are a number of previous studies which suggest that returns are higher to 
attending schools where students have higher SAT scores, but none of these do a very 
good job of controlling for the unobserved characteristics of the persons attending 
the schools. Krueger does this in a recent study by controlling for the quality of the 
schools you were accepted to (not everyone goes to the best school that accepts them) 
and finds that average SAT scores don't matter but tuition does. I am not convinced 
that the identification is bullet proof nor that the result might not be sensitive to 
specification. Particularly since average SAT score at schools is always badly 
mismeasured (either because the schools misreport them or because of the limited 
samples used to estimate them). 
-- Bill Dickens

William T. Dickens
The Brookings Institution
1775 Massachusetts Avenue, NW
Washington, DC 20036
Phone: (202) 797-6113
FAX:     (202) 797-6181
AOL IM: wtdickens

Reply via email to