The data files used for the examples in this text can be downloaded in a zip file from the Stata Web site. You can then use a program such as zip to unzip the data files.
Example 19.1 on page 652 using fertil2.dta.
use fertil2, clear
reg children educ age agesq evermarr urban electric tv
Source | SS df MS Number of obs = 4358
-------------+------------------------------ F( 7, 4350) = 893.91
Model | 12688.9349 7 1812.70499 Prob > F = 0.0000
Residual | 8821.09719 4350 2.02783843 R-squared = 0.5899
-------------+------------------------------ Adj R-squared = 0.5892
Total | 21510.0321 4357 4.93689055 Root MSE = 1.424
------------------------------------------------------------------------------
children | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
educ | -.0644086 .0063199 -10.19 0.000 -.0767987 -.0520184
age | .2724736 .017019 16.01 0.000 .2391077 .3058395
agesq | -.0019067 .000274 -6.96 0.000 -.0024438 -.0013696
evermarr | .6822725 .052167 13.08 0.000 .5799986 .7845463
urban | -.2278933 .0458653 -4.97 0.000 -.3178126 -.137974
electric | -.2617394 .0758688 -3.45 0.001 -.410481 -.1129979
tv | -.2499509 .0901474 -2.77 0.006 -.4266858 -.0732161
_cons | -3.39384 .2445496 -13.88 0.000 -3.873281 -2.914398
------------------------------------------------------------------------------
glm children educ age agesq evermarr urban electric tv, fam(poisson) link(log) robust
Generalized linear models No. of obs = 4358
Optimization : ML: Newton-Raphson Residual df = 4350
Scale parameter = 1
Deviance = 3908.76293 (1/df) Deviance = .8985662
Pearson = 3265.867362 (1/df) Pearson = .7507741
Variance function: V(u) = u [Poisson]
Link function : g(u) = ln(u) [Log]
Standard errors : Sandwich
Log pseudo-likelihood = -6497.059873 AIC = 2.985342
BIC =-32543.23011
------------------------------------------------------------------------------
| Robust
children | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
educ | -.0216645 .0025918 -8.36 0.000 -.0267442 -.0165847
age | .3373308 .0094473 35.71 0.000 .3188144 .3558473
agesq | -.0041158 .000144 -28.57 0.000 -.0043981 -.0038335
evermarr | .314751 .0232117 13.56 0.000 .269257 .360245
urban | -.0860549 .0200471 -4.29 0.000 -.1253465 -.0467633
electric | -.1205347 .0372925 -3.23 0.001 -.1936266 -.0474428
tv | -.1447046 .0438055 -3.30 0.001 -.2305617 -.0588475
_cons | -5.374829 .1477633 -36.37 0.000 -5.66444 -5.085219
------------------------------------------------------------------------------
predict res, r
(3 missing values generated)
predict p
(option mu assumed; predicted mean children)
(3 missing values generated)
gen stdressq = res^2/p
(3 missing values generated)
sum stdressq
Variable | Obs Mean Std. Dev. Min Max
-------------+--------------------------------------------------------
stdressq | 4358 .7493959 1.076655 6.55e-07 14.37877
di sqrt(r(mean)*r(N)/(r(N)-7)) /*R-squared for Poisson regression*/
.86637264
Example 19.2 on page 665 using fertil2.dta.
reg educ frsthalf age agesq evermarr urban electric tv
Source | SS df MS Number of obs = 4358
-------------+------------------------------ F( 7, 4350) = 208.02
Model | 16850.0414 7 2407.14877 Prob > F = 0.0000
Residual | 50336.75 4350 11.5716667 R-squared = 0.2508
-------------+------------------------------ Adj R-squared = 0.2496
Total | 67186.7914 4357 15.4204249 Root MSE = 3.4017
------------------------------------------------------------------------------
educ | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
frsthalf | -.6361072 .1038091 -6.13 0.000 -.8396258 -.4325885
age | -.0702853 .0406438 -1.73 0.084 -.1499678 .0093971
agesq | -.0008118 .0006544 -1.24 0.215 -.0020947 .0004711
evermarr | -.8023536 .1241223 -6.46 0.000 -1.045697 -.5590106
urban | .8637296 .108786 7.94 0.000 .6504536 1.077006
electric | 1.977712 .1787579 11.06 0.000 1.627255 2.328168
tv | 2.714666 .2113782 12.84 0.000 2.300257 3.129075
_cons | 8.20343 .5752279 14.26 0.000 7.075691 9.33117
------------------------------------------------------------------------------
predict r, r
(3 missing values generated)
glm children educ age agesq evermarr urban electric tv r, fam(poisson) link(log) robust
Generalized linear models No. of obs = 4358
Optimization : ML: Newton-Raphson Residual df = 4349
Scale parameter = 1
Deviance = 3908.184386 (1/df) Deviance = .8986398
Pearson = 3264.568982 (1/df) Pearson = .7506482
Variance function: V(u) = u [Poisson]
Link function : g(u) = ln(u) [Log]
Standard errors : Sandwich
Log pseudo-likelihood = -6496.7706 AIC = 2.985668
BIC =-32535.42889
------------------------------------------------------------------------------
| Robust
children | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
educ | -.0459847 .0295654 -1.56 0.120 -.1039319 .0119625
age | .3357196 .0097048 34.59 0.000 .3166986 .3547405
agesq | -.0041373 .0001451 -28.52 0.000 -.0044216 -.0038529
evermarr | .2941007 .0343224 8.57 0.000 .22683 .3613714
urban | -.0647957 .0323494 -2.00 0.045 -.1281994 -.001392
electric | -.0711916 .0688407 -1.03 0.301 -.2061168 .0637337
tv | -.0780223 .0937508 -0.83 0.405 -.2617705 .1057258
r | .024515 .0296235 0.83 0.408 -.033546 .0825761
_cons | -5.18482 .2767832 -18.73 0.000 -5.727305 -4.642335
------------------------------------------------------------------------------