heckman earn cols exp male ethblack ethhisp asvabc, ///
> sel(cols exp male ethblack ethhisp asvabc)
Iteration 0: log likelihood = -5662.3114 (not concave)
Iteration 1: log likelihood = -2038.6067 (not concave)
Iteration 2: log likelihood = -1402.3628 (not concave)
Iteration 3: log likelihood = -1232.5342 (not concave)
Iteration 4: log likelihood = -1225.4769 (not concave)
Iteration 5: log likelihood = -1225.4286
Iteration 6: log likelihood = -1225.3111
Iteration 7: log likelihood = -1225.3111 (not concave)
Iteration 8: log likelihood = -1225.3111 (backed up)
Heckman selection model Number of obs = 540
(regression model with sample selection) Censored obs = 255
Uncensored obs = 285
Wald chi2(6) = 76.11
Log likelihood = -1225.311 Prob > chi2 = 0.0000
earn Coef. Std. Err. z P>z [95% Conf. Interval]
earn
cols 2.71381 .6961264 3.90 0.000 1.349427 4.078192
exp -.0422218 .3091996 -0.14 0.891 -.6482419 .5637983
male 10.11557 2.1745 4.65 0.000 5.853625 14.37751
ethblack -.8792997 3.789981 -0.23 0.817 -8.307525 6.548926
ethhisp 1.101057 4.918532 0.22 0.823 -8.53909 10.7412
asvabc .287441 .1669076 1.72 0.085 -.0396919 .614574
_cons -5.661931 9.768398 -0.58 0.562 -24.80764 13.48378
select
cols 12.80089 2.15e+09 0.00 1.000 -4.21e+09 4.21e+09
exp -.0149469 20131.92 -0.00 1.000 -39457.86 39457.83
male -.30282 394808.8 -0.00 1.000 -773811.3 773810.7
ethblack -.2484062 492365 -0.00 1.000 -965017.8 965017.3
ethhisp -.3924443 1330305 -0.00 1.000 -2607351 2607350
asvabc -.0072675 14207.3 -0.00 1.000 -27845.81 27845.8
_cons -7.021019 668325.3 -0.00 1.000 -1309900 1309886
/athrho 1.4692 6.35e+08 0.00 1.000 -1.25e+09 1.25e+09
/lnsigma 2.880399 .0418854 68.77 0.000 2.798305 2.962493
rho .8994248 1.21e+08 -1 1
sigma 17.82138 .7464555 16.41679 19.34613
lambda 16.02899 2.16e+09 -4.24e+09 4.24e+09
LR test of indep. eqns. (rho = 0): chi2(1) = 0.00 Prob > chi2 = 0.9996
. mfx
Marginal effects after heckman
y = Linear prediction (predict)
= 18.240847
variable dy/dx Std. Err. z P>z [ 95% C.I. ] X
cols 2.71381 .69613 3.90 0.000 1.34943 4.07819 1.83704
exp -.0422218 .3092 -0.14 0.891 -.648241 .563797 17.0224
male* 10.11557 2.1745 4.65 0.000 5.85362 14.3775 .498148
ethblack* -.8792997 3.78998 -0.23 0.817 -8.30753 6.54893 .111111
ethhisp* 1.101057 4.91853 0.22 0.823 -8.53909 10.7412 .061111
asvabc .287441 .16691 1.72 0.085 -.039692 .614574 50.8887
(*) dy/dx is for discrete change of dummy variable from 0 to 1
.
end of do-file