Bryan Caplan

What's Wrong With IVs? [wonkish]

Summers believes we can reduce... Free Market Economics Books Bl...
Labor economists love using instrumental variables - like your distance to the nearest college - to estimate the education premiumHeckman, Lochner, and Todd point out a recurring problem with this approach:
[M]ost of the candidates for instrumental variables in the literature are also correlated with cognitive ability. Therefore, in data sets where cognitive ability is not available most of these variables are not valid instruments since they violate the crucial IV assumption of independence. Since few data sets have measures of cognitive ability, this finding calls into question much of the IV literature. Notice that the local unemployment rate is not strongly correlated with AFQT. However, it is only weakly correlated with college attendance.
Check it out:

Comments and Sharing

COMMENTS (2 to date)
bren writes:

How about the regression discontinuity approach?

While the method won't distinguish between why more education might lead to higher earnings (signalling vs human capital), comparing people on either side of a threshold should help with the cognetive selection effects, no?

Steve Sailer writes:

"like your distance to the nearest college"

Neal Stephenson likes to point out the long list of bright people who grew up, like him, in college towns.

Comments for this entry have been closed
Return to top