I've occasionally heard that instrumental variables (IV) estimators of
the return to education yield markedly higher estimates than OLS. Is
this true? And how can this make any intuitive sense? If IV is
correcting for endogeneity, you would expect things to go the other
way.
Why? With a medical treatment, you would expect endogeneity to
understate the benefit, because sicker people are more likely to
voluntarily seek treatment. But with education, you would expect
endogeneity to overstate the benefit, because able people are more
likely to voluntarily enroll.
--
Prof. Bryan Caplan
Department of Economics George Mason University
http://www.bcaplan.com [EMAIL PROTECTED]
"He wrote a letter, but did not post it because he felt that no one
would have understood what he wanted to say, and besides it was not
necessary that anyone but himself should understand it."
Leo Tolstoy, *The Cossacks*
