------------------------------------------------------------------------------------------------- name: log: /Users/nataliapoiatti/PRI5034/Aula Heterocedasticidade Stata.log log type: text opened on: 29 Apr 2021, 16:17:45 . use "/Users/nataliapoiatti/Downloads/WAGE1 (5).DTA" . sum wage Variable | Obs Mean Std. Dev. Min Max -------------+-------------------------------------------------------- wage | 526 5.896103 3.693086 .53 24.98 . sum wage, detail average hourly earnings ------------------------------------------------------------- Percentiles Smallest 1% 1.67 .53 5% 2.75 1.43 10% 2.92 1.5 Obs 526 25% 3.33 1.5 Sum of Wgt. 526 50% 4.65 Mean 5.896103 Largest Std. Dev. 3.693086 75% 6.88 21.86 90% 10 22.2 Variance 13.63888 95% 13 22.86 Skewness 2.007325 99% 20 24.98 Kurtosis 7.970083 . twoway (scatter wage educ) . sum wage if female==1 Variable | Obs Mean Std. Dev. Min Max -------------+-------------------------------------------------------- wage | 252 4.587659 2.529363 .53 21.63 . tab female, sum(wage) =1 if | Summary of average hourly earnings female | Mean Std. Dev. Freq. ------------+------------------------------------ 0 | 7.1 4.2 274 1 | 4.6 2.5 252 ------------+------------------------------------ Total | 5.9 3.7 526 . reg wage educ exper female Source | SS df MS Number of obs = 526 -------------+------------------------------ F( 3, 522) = 77.92 Model | 2214.74206 3 738.247353 Prob > F = 0.0000 Residual | 4945.67223 522 9.47446788 R-squared = 0.3093 -------------+------------------------------ Adj R-squared = 0.3053 Total | 7160.41429 525 13.6388844 Root MSE = 3.0781 ------------------------------------------------------------------------------ wage | Coef. Std. Err. t P>|t| [95% Conf. Interval] -------------+---------------------------------------------------------------- educ | .6025802 .0511174 11.79 0.000 .5021591 .7030012 exper | .0642417 .0104003 6.18 0.000 .0438101 .0846734 female | -2.155517 .2703055 -7.97 0.000 -2.686537 -1.624497 _cons | -1.734481 .7536203 -2.30 0.022 -3.214982 -.2539797 ------------------------------------------------------------------------------ . test educ exper female ( 1) educ = 0 ( 2) exper = 0 ( 3) female = 0 F( 3, 522) = 77.92 Prob > F = 0.0000 . test (educ=1) (exper=0) (female=0) ( 1) educ = 1 ( 2) exper = 0 ( 3) female = 0 F( 3, 522) = 66.20 Prob > F = 0.0000 . test (educ=exper) ( 1) educ - exper = 0 F( 1, 522) = 120.88 Prob > F = 0.0000 . generate educ_exper=educ*exper . reg wage educ exper female educ_exper Source | SS df MS Number of obs = 526 -------------+------------------------------ F( 4, 521) = 59.06 Model | 2233.98776 4 558.496939 Prob > F = 0.0000 Residual | 4926.42653 521 9.45571312 R-squared = 0.3120 -------------+------------------------------ Adj R-squared = 0.3067 Total | 7160.41429 525 13.6388844 Root MSE = 3.075 ------------------------------------------------------------------------------ wage | Coef. Std. Err. t P>|t| [95% Conf. Interval] -------------+---------------------------------------------------------------- educ | .5044418 .0856723 5.89 0.000 .3361363 .6727474 exper | .0084381 .0404714 0.21 0.835 -.0710691 .0879452 female | -2.194 .2713817 -8.08 0.000 -2.727137 -1.660863 educ_exper | .004722 .0033099 1.43 0.154 -.0017803 .0112244 _cons | -.4899717 1.152289 -0.43 0.671 -2.753676 1.773732 ------------------------------------------------------------------------------ . test educ educ_exper ( 1) educ = 0 ( 2) educ_exper = 0 F( 2, 521) = 70.64 Prob > F = 0.0000 . reg wage educ exper female Source | SS df MS Number of obs = 526 -------------+------------------------------ F( 3, 522) = 77.92 Model | 2214.74206 3 738.247353 Prob > F = 0.0000 Residual | 4945.67223 522 9.47446788 R-squared = 0.3093 -------------+------------------------------ Adj R-squared = 0.3053 Total | 7160.41429 525 13.6388844 Root MSE = 3.0781 ------------------------------------------------------------------------------ wage | Coef. Std. Err. t P>|t| [95% Conf. Interval] -------------+---------------------------------------------------------------- educ | .6025802 .0511174 11.79 0.000 .5021591 .7030012 exper | .0642417 .0104003 6.18 0.000 .0438101 .0846734 female | -2.155517 .2703055 -7.97 0.000 -2.686537 -1.624497 _cons | -1.734481 .7536203 -2.30 0.022 -3.214982 -.2539797 ------------------------------------------------------------------------------ . predict u, res . gen u2=u^2 . reg u2 educ exper female Source | SS df MS Number of obs = 526 -------------+------------------------------ F( 3, 522) = 13.13 Model | 22587.9402 3 7529.31342 Prob > F = 0.0000 Residual | 299359.526 522 573.485683 R-squared = 0.0702 -------------+------------------------------ Adj R-squared = 0.0648 Total | 321947.467 525 613.23327 Root MSE = 23.948 ------------------------------------------------------------------------------ u2 | Coef. Std. Err. t P>|t| [95% Conf. Interval] -------------+---------------------------------------------------------------- educ | 1.881484 .3976972 4.73 0.000 1.1002 2.662767 exper | .2694904 .0809153 3.33 0.001 .1105307 .4284501 female | -6.365282 2.102997 -3.03 0.003 -10.49666 -2.233904 _cons | -15.77059 5.863223 -2.69 0.007 -27.289 -4.252172 ------------------------------------------------------------------------------ . reg wage educ exper female Source | SS df MS Number of obs = 526 -------------+------------------------------ F( 3, 522) = 77.92 Model | 2214.74206 3 738.247353 Prob > F = 0.0000 Residual | 4945.67223 522 9.47446788 R-squared = 0.3093 -------------+------------------------------ Adj R-squared = 0.3053 Total | 7160.41429 525 13.6388844 Root MSE = 3.0781 ------------------------------------------------------------------------------ wage | Coef. Std. Err. t P>|t| [95% Conf. Interval] -------------+---------------------------------------------------------------- educ | .6025802 .0511174 11.79 0.000 .5021591 .7030012 exper | .0642417 .0104003 6.18 0.000 .0438101 .0846734 female | -2.155517 .2703055 -7.97 0.000 -2.686537 -1.624497 _cons | -1.734481 .7536203 -2.30 0.022 -3.214982 -.2539797 ------------------------------------------------------------------------------ . estat hettest, rhs iid Breusch-Pagan / Cook-Weisberg test for heteroskedasticity Ho: Constant variance Variables: educ exper female chi2(3) = 36.90 Prob > chi2 = 0.0000 . display 526*0.0702 36.9252 . estat imtest, preserve white White's test for Ho: homoskedasticity against Ha: unrestricted heteroskedasticity chi2(8) = 63.41 Prob > chi2 = 0.0000 Cameron & Trivedi's decomposition of IM-test --------------------------------------------------- Source | chi2 df p ---------------------+----------------------------- Heteroskedasticity | 63.41 8 0.0000 Skewness | 31.28 3 0.0000 Kurtosis | 9.61 1 0.0019 ---------------------+----------------------------- Total | 104.31 12 0.0000 --------------------------------------------------- . . reg wage educ exper female , robust Linear regression Number of obs = 526 F( 3, 522) = 51.41 Prob > F = 0.0000 R-squared = 0.3093 Root MSE = 3.0781 ------------------------------------------------------------------------------ | Robust wage | Coef. Std. Err. t P>|t| [95% Conf. Interval] -------------+---------------------------------------------------------------- educ | .6025802 .0641895 9.39 0.000 .4764786 .7286817 exper | .0642417 .010044 6.40 0.000 .0445102 .0839733 female | -2.155517 .2591294 -8.32 0.000 -2.664582 -1.646453 _cons | -1.734481 .8577554 -2.02 0.044 -3.419558 -.0494042 ------------------------------------------------------------------------------ . reg wage educ exper female Source | SS df MS Number of obs = 526 -------------+------------------------------ F( 3, 522) = 77.92 Model | 2214.74206 3 738.247353 Prob > F = 0.0000 Residual | 4945.67223 522 9.47446788 R-squared = 0.3093 -------------+------------------------------ Adj R-squared = 0.3053 Total | 7160.41429 525 13.6388844 Root MSE = 3.0781 ------------------------------------------------------------------------------ wage | Coef. Std. Err. t P>|t| [95% Conf. Interval] -------------+---------------------------------------------------------------- educ | .6025802 .0511174 11.79 0.000 .5021591 .7030012 exper | .0642417 .0104003 6.18 0.000 .0438101 .0846734 female | -2.155517 .2703055 -7.97 0.000 -2.686537 -1.624497 _cons | -1.734481 .7536203 -2.30 0.022 -3.214982 -.2539797 ------------------------------------------------------------------------------ . predict u, res u already defined r(110); . gen lu2=log(u2) . reg lu2 educ exper female Source | SS df MS Number of obs = 526 -------------+------------------------------ F( 3, 522) = 22.59 Model | 415.266537 3 138.422179 Prob > F = 0.0000 Residual | 3198.438 522 6.12727587 R-squared = 0.1149 -------------+------------------------------ Adj R-squared = 0.1098 Total | 3613.70454 525 6.88324674 Root MSE = 2.4753 ------------------------------------------------------------------------------ lu2 | Coef. Std. Err. t P>|t| [95% Conf. Interval] -------------+---------------------------------------------------------------- educ | .2126023 .0411079 5.17 0.000 .1318451 .2933594 exper | .0456081 .0083638 5.45 0.000 .0291772 .0620389 female | -.9165781 .2173758 -4.22 0.000 -1.343617 -.4895393 _cons | -2.553791 .6060506 -4.21 0.000 -3.744389 -1.363194 ------------------------------------------------------------------------------ . predict lu2_hat (option xb assumed; fitted values) . gen elu2_hat=exp(lu2_hat) . reg wage educ exper female [aweight=elu2_hat] (sum of wgt is 1.2186e+03) Source | SS df MS Number of obs = 526 -------------+------------------------------ F( 3, 522) = 73.09 Model | 3495.36861 3 1165.12287 Prob > F = 0.0000 Residual | 8321.59047 522 15.9417442 R-squared = 0.2958 -------------+------------------------------ Adj R-squared = 0.2917 Total | 11816.9591 525 22.5084935 Root MSE = 3.9927 ------------------------------------------------------------------------------ wage | Coef. Std. Err. t P>|t| [95% Conf. Interval] -------------+---------------------------------------------------------------- educ | .838811 .069909 12.00 0.000 .7014734 .9761486 exper | .0716714 .0132004 5.43 0.000 .045739 .0976039 female | -2.791052 .4118124 -6.78 0.000 -3.600065 -1.982038 _cons | -4.752544 1.135241 -4.19 0.000 -6.982746 -2.522342 ------------------------------------------------------------------------------ . reg wage educ exper female , robust Linear regression Number of obs = 526 F( 3, 522) = 51.41 Prob > F = 0.0000 R-squared = 0.3093 Root MSE = 3.0781 ------------------------------------------------------------------------------ | Robust wage | Coef. Std. Err. t P>|t| [95% Conf. Interval] -------------+---------------------------------------------------------------- educ | .6025802 .0641895 9.39 0.000 .4764786 .7286817 exper | .0642417 .010044 6.40 0.000 .0445102 .0839733 female | -2.155517 .2591294 -8.32 0.000 -2.664582 -1.646453 _cons | -1.734481 .8577554 -2.02 0.044 -3.419558 -.0494042 ------------------------------------------------------------------------------ . log close name: log: /Users/nataliapoiatti/PRI5034/Aula Heterocedasticidade Stata.log log type: text closed on: 29 Apr 2021, 17:03:42 --------------------------------------------------------------------------------------------------------------------