jhorsman wrote:
>
> At 12:23 PM 10/24/00 -0500, you wrote:
>
> >Informal Survey:
> >
> >What are the big unsolved puzzles of economic empirical research?
> >What economic phenoma seem pretty darn important, but have not
> >been adequately explained by current economic theories?
> >
> >Just curious to see what the pro's have to say...
> >
> >1- How much of the price of college is consumption?
>
> 2- What % of wages is due to i.q. and what are the other factors?
That one is pretty easily answered using NLSY data. Here's one fairly
canonical rate of return to education regression:
Dependent Variable: LOG(LABINC)
Method: Least Squares
Date: 10/25/00 Time: 11:37
Sample(adjusted): 2 12679
Included observations: 4293
Excluded observations: 8385 after adjusting endpoints
Var Coefficient Std. Error t-Statistic Prob.
C 7.833828 0.199817 39.20496 0.0000
GRADE 0.103397 0.011028 9.375956 0.0000
AFQT 0.005351 0.000733 7.302130 0.0000
EXPER 0.029510 0.006679 4.417953 0.0000
BLACK -0.052849 0.037939 -1.392999 0.1637
OTHRACE 0.143826 0.063003 2.282850 0.0225
MALE -0.035547 0.070648 -0.503157 0.6149
MARRIED*MALE 0.445561 0.046091 9.666995 0.0000
MARRIED*(1-MALE)-0.092897 0.044369 -2.093725 0.0363
CHILDNUM*MALE -0.034955 0.018965 -1.843140 0.0654
CHILDNUM*(1-MALE)-0.201206 0.019986 -10.06741 0.0000
R-squared 0.227655 Mean dependent var 9.630587
The dependent variable is the log of annual labor earnings (which drops
out 0-earners from the data set).
The independent variables are:
GRADE - years of education
AFQT - percentile on the AFQT test, essentially an IQ measure
EXPER - years of experience
BLACK
OTHRACE
MALE
MARRIED*MALE
MARRIED*(1-MALE)
CHILDNUM*MALE - number of children interacted with male
CHILDNUM*(1-MALE) - number of children interacted with female
In answer to your question, then, each IQ percentile on average raises
your annual labor earnings by .5%; each year of school raises them by
10.3%.
Of course you can fiddle with these results, but most of them look
roughly like this.
--
Prof. Bryan Caplan [EMAIL PROTECTED]
http://www.gmu.edu/departments/economics/bcaplan
"We may be dissatisfied with television for two quite different
reasons: because our set does not work, or because we dislike
the program we are receiving. Similarly, we may be dissatisfied
with ourselves for two quite different reasons: because our body
does not work (bodily illness), or because we dislike our
conduct (mental illness)."
--Thomas Szasz, *The Untamed Tongue*