Bill is quite correct that variation in "discount rates," (which could also be something like how much you enjoy schooling for its own sake) can explain the fact that IV estimates are higher than OLS estimates. Bryan's question, however, can be rephrased as not how do you explain the data (low ability bias and high discount rate bias) but why is it that ability bias appears low? In other words aren't there good grounds for thinking that ability bias is large? And if so how is it that this doesn't show up in the data?
Alex -- Alexander Tabarrok Department of Economics, MSN 1D3 George Mason University Fairfax, VA, 22030 Tel. 703-993-2314 and Director of Research The Independent Institute 100 Swan Way Oakland, CA, 94621 Tel. 510-632-1366
