发帖
雷达卡
最近在研究男女工资差异，刚结束筛选数据阶段。现在在做oaxaca在stata中的实现。
下面是结果。
. oaxaca lnincome edu exp expsq party married kgender2 kgender3 area2 area3, by (gender) noisily detail cluster (id)
Model for group 1
Source | SS df MS Number of obs = 3364
-------------+------------------------------ F( 9, 3354) = 96.68
Model | 413.061403 9 45.8957114 Prob > F = 0.0000
Residual | 1592.25934 3354 .474734447 R-squared = 0.2060
-------------+------------------------------ Adj R-squared = 0.2039
Total | 2005.32074 3363 .596289247 Root MSE = .68901
------------------------------------------------------------------------------
lnincome | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
edu | .0643783 .0038048 16.92 0.000 .0569184 .0718382
exp | .024276 .0057829 4.20 0.000 .0129377 .0356144
expsq | -.000548 .0001145 -4.79 0.000 -.0007725 -.0003235
party | .19782 .0343456 5.76 0.000 .1304795 .2651605
married | .2331533 .0488086 4.78 0.000 .1374556 .3288509
kgender2 | -.0619755 .0533061 -1.16 0.245 -.1664913 .0425404
kgender3 | -.0405377 .0530735 -0.76 0.445 -.1445974 .063522
area2 | -.0802683 .0382017 -2.10 0.036 -.1551693 -.0053673
area3 | .3427523 .0272112 12.60 0.000 .2894 .3961046
_cons | 8.717215 .0722709 120.62 0.000 8.575516 8.858915
------------------------------------------------------------------------------
Model for group 2
Source | SS df MS Number of obs = 2301
-------------+------------------------------ F( 9, 2291) = 81.60
Model | 335.727677 9 37.3030752 Prob > F = 0.0000
Residual | 1047.32405 2291 .457147119 R-squared = 0.2427
-------------+------------------------------ Adj R-squared = 0.2398
Total | 1383.05173 2300 .601326838 Root MSE = .67613
------------------------------------------------------------------------------
lnincome | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
edu | .081869 .0043991 18.61 0.000 .0732424 .0904957
exp | .0354111 .0072748 4.87 0.000 .0211452 .049677
expsq | -.0007656 .0001665 -4.60 0.000 -.0010922 -.0004391
party | .208627 .0538424 3.87 0.000 .103042 .3142119
married | .0971665 .0508282 1.91 0.056 -.0025076 .1968406
kgender2 | -.1480145 .060788 -2.43 0.015 -.2672198 -.0288092
kgender3 | -.1397136 .0606033 -2.31 0.021 -.2585566 -.0208706
area2 | -.0073612 .0462328 -0.16 0.874 -.0980237 .0833013
area3 | .2842073 .0324643 8.75 0.000 .2205447 .3478698
_cons | 8.305193 .0817298 101.62 0.000 8.144921 8.465465
------------------------------------------------------------------------------
Blinder-Oaxaca decomposition Number of obs = 5665
1: gender = 0
2: gender = 1
(Std. Err. adjusted for 3842 clusters in id)
------------------------------------------------------------------------------
| Robust
lnincome | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
Differential |
Prediction_1 | 9.954145 .0136762 727.84 0.000 9.92734 9.98095
Prediction_2 | 9.628072 .0164587 584.99 0.000 9.595813 9.66033
Difference | .3260736 .0188346 17.31 0.000 .2891585 .3629888
-------------+----------------------------------------------------------------
Endowments |
edu | -.0119532 .0075475 -1.58 0.113 -.026746 .0028395
exp | .1015494 .023578 4.31 0.000 .0553374 .1477615
expsq | -.1060623 .0258648 -4.10 0.000 -.1567563 -.0553683
party | .0186526 .0050144 3.72 0.000 .0088245 .0284807
married | .0011023 .0011103 0.99 0.321 -.0010738 .0032784
kgender2 | -.0000878 .0014207 -0.06 0.951 -.0028723 .0026967
kgender3 | -.0009889 .0014165 -0.70 0.485 -.0037652 .0017874
area2 | -.000029 .0001804 -0.16 0.872 -.0003825 .0003246
area3 | -.0046628 .0028406 -1.64 0.101 -.0102303 .0009048
Total | -.0024796 .0118912 -0.21 0.835 -.0257859 .0208266
-------------+----------------------------------------------------------------
Coefficients |
edu | -.1830715 .0600995 -3.05 0.002 -.3008643 -.0652787
exp | -.2221978 .1810806 -1.23 0.220 -.5771093 .1327138
expsq | .1095283 .1017277 1.08 0.282 -.0898544 .308911
party | -.0008971 .0051879 -0.17 0.863 -.0110652 .0092711
married | .1137064 .0598786 1.90 0.058 -.0036535 .2310664
kgender2 | .0334285 .0295408 1.13 0.258 -.0244705 .0913274
kgender3 | .041722 .0316337 1.32 0.187 -.0202789 .1037228
area2 | -.0102026 .0074424 -1.37 0.170 -.0247895 .0043844
area3 | .0336615 .0221131 1.52 0.128 -.0096794 .0770024
_cons | .4120225 .1058155 3.89 0.000 .204628 .6194169
Total | .3277002 .0174302 18.80 0.000 .2935376 .3618629
-------------+----------------------------------------------------------------
Interaction |
edu | .0025537 .001812 1.41 0.159 -.0009977 .0061051
exp | -.0319323 .0261583 -1.22 0.222 -.0832016 .0193369
expsq | .0301496 .0280857 1.07 0.283 -.0248974 .0851966
party | -.0009662 .0055882 -0.17 0.863 -.0119188 .0099864
married | .0015427 .0015123 1.02 0.308 -.0014213 .0045068
kgender2 | .0000511 .0008268 0.06 0.951 -.0015694 .0016715
kgender3 | .000702 .0010915 0.64 0.520 -.0014374 .0028413
area2 | -.000287 .0005436 -0.53 0.597 -.0013526 .0007785
area3 | -.0009605 .0008533 -1.13 0.260 -.0026329 .0007119
--more--
新人刚学习stata，好不容易找到了oaxaca分解的stata指令，但是对结果却不知道怎么下手。
endowments. coefficient. interaction. 都代表什么意思呢？
如果我想计算每个indep var 对男女工资差异的解释大小，我该选用哪些有用的信息来进行计算呢？
希望对oaxaca有所了解的朋友指导我一下啦！谢谢啦！
京公网安备 11010802022788号
