|
|
|
||||
|
|
|||||
The data files used for the examples in this text can be downloaded in a .zip file from the Wiley Publications website. You can then use a program such as WinZip to unzip the data files. If you need assistance getting data into Stata, please see our Stata Class Notes, especially the unit on Entering Data. (NOTE: The *.dat files are the data files, and the *.txt files contain the codebook information.)
Table 4.1, page 105.
use "d:\hosmer\uis.dta", clear
logit dfree age
Iteration 0: log likelihood = -326.86446
Iteration 1: log likelihood = -326.16602
Iteration 2: log likelihood = -326.16544
Logit estimates Number of obs = 575
LR chi2(1) = 1.40
Prob > chi2 = 0.2371
Log likelihood = -326.16544 Pseudo R2 = 0.0021
------------------------------------------------------------------------------
dfree | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
age | .0181723 .015344 1.18 0.236 -.0119014 .048246
_cons | -1.660226 .5110844 -3.25 0.001 -2.661933 -.6585194
------------------------------------------------------------------------------
logit dfree age, or
Iteration 0: log likelihood = -326.86446
Iteration 1: log likelihood = -326.16602
Iteration 2: log likelihood = -326.16544
Logit estimates Number of obs = 575
LR chi2(1) = 1.40
Prob > chi2 = 0.2371
Log likelihood = -326.16544 Pseudo R2 = 0.0021
------------------------------------------------------------------------------
dfree | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
age | 1.018338 .0156254 1.18 0.236 .9881691 1.049429
------------------------------------------------------------------------------
lrtest, saving(1)
logit dfree
Iteration 0: log likelihood = -326.86446
Logit estimates Number of obs = 575
LR chi2(0) = -0.00
Prob > chi2 = .
Log likelihood = -326.86446 Pseudo R2 = -0.0000
------------------------------------------------------------------------------
dfree | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
_cons | -1.068691 .095599 -11.18 0.000 -1.256061 -.88132
------------------------------------------------------------------------------
lrtest, using(1)
Logit: likelihood-ratio test chi2(1) = 1.40
Prob > chi2 = 0.2371
logit dfree beck
Iteration 0: log likelihood = -326.86446
Iteration 1: log likelihood = -326.54634
Iteration 2: log likelihood = -326.54621
Logit estimates Number of obs = 575
LR chi2(1) = 0.64
Prob > chi2 = 0.4250
Log likelihood = -326.54621 Pseudo R2 = 0.0010
------------------------------------------------------------------------------
dfree | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
beck | -.008225 .0103428 -0.80 0.426 -.0284965 .0120464
_cons | -.9272829 .2003166 -4.63 0.000 -1.319896 -.5346696
------------------------------------------------------------------------------
logit dfree beck, or
Iteration 0: log likelihood = -326.86446
Iteration 1: log likelihood = -326.54634
Iteration 2: log likelihood = -326.54621
Logit estimates Number of obs = 575
LR chi2(1) = 0.64
Prob > chi2 = 0.4250
Log likelihood = -326.54621 Pseudo R2 = 0.0010
------------------------------------------------------------------------------
dfree | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
beck | .9918087 .010258 -0.80 0.426 .9719057 1.012119
------------------------------------------------------------------------------
lrtest, saving(2)
logit dfree
Iteration 0: log likelihood = -326.86446
Logit estimates Number of obs = 575
LR chi2(0) = -0.00
Prob > chi2 = .
Log likelihood = -326.86446 Pseudo R2 = -0.0000
------------------------------------------------------------------------------
dfree | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
_cons | -1.068691 .095599 -11.18 0.000 -1.256061 -.88132
------------------------------------------------------------------------------
lrtest, using(2)
Logit: likelihood-ratio test chi2(1) = 0.64
Prob > chi2 = 0.4250
logit dfree ndrugtx
Iteration 0: log likelihood = -326.86446
Iteration 1: log likelihood = -321.33296
Iteration 2: log likelihood = -320.94874
Iteration 3: log likelihood = -320.94485
Iteration 4: log likelihood = -320.94485
Logit estimates Number of obs = 575
LR chi2(1) = 11.84
Prob > chi2 = 0.0006
Log likelihood = -320.94485 Pseudo R2 = 0.0181
------------------------------------------------------------------------------
dfree | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
ndrugtx | -.0749582 .024681 -3.04 0.002 -.123332 -.0265844
_cons | -.7677805 .130326 -5.89 0.000 -1.023215 -.5123462
------------------------------------------------------------------------------
logit dfree ndrugtx, or
Iteration 0: log likelihood = -326.86446
Iteration 1: log likelihood = -321.33296
Iteration 2: log likelihood = -320.94874
Iteration 3: log likelihood = -320.94485
Iteration 4: log likelihood = -320.94485
Logit estimates Number of obs = 575
LR chi2(1) = 11.84
Prob > chi2 = 0.0006
Log likelihood = -320.94485 Pseudo R2 = 0.0181
------------------------------------------------------------------------------
dfree | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
ndrugtx | .9277822 .0228986 -3.04 0.002 .8839701 .9737658
------------------------------------------------------------------------------
lrtest, saving(3)
logit dfree
Iteration 0: log likelihood = -326.86446
Logit estimates Number of obs = 575
LR chi2(0) = -0.00
Prob > chi2 = .
Log likelihood = -326.86446 Pseudo R2 = -0.0000
------------------------------------------------------------------------------
dfree | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
_cons | -1.068691 .095599 -11.18 0.000 -1.256061 -.88132
------------------------------------------------------------------------------
lrtest, using(3)
Logit: likelihood-ratio test chi2(1) = 11.84
Prob > chi2 = 0.0006
logit dfree ivhx2 ivhx3
Iteration 0: log likelihood = -326.86446
Iteration 1: log likelihood = -320.24478
Iteration 2: log likelihood = -320.18821
Iteration 3: log likelihood = -320.18821
Logit estimates Number of obs = 575
LR chi2(2) = 13.35
Prob > chi2 = 0.0013
Log likelihood = -320.18821 Pseudo R2 = 0.0204
------------------------------------------------------------------------------
dfree | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
ivhx2 | -.4810199 .2657063 -1.81 0.070 -1.001795 .0397548
ivhx3 | -.7748382 .2165765 -3.58 0.000 -1.19932 -.3503561
_cons | -.6797242 .1417395 -4.80 0.000 -.9575285 -.4019198
------------------------------------------------------------------------------
logit dfree ivhx2 ivhx3, or
Iteration 0: log likelihood = -326.86446
Iteration 1: log likelihood = -320.24478
Iteration 2: log likelihood = -320.18821
Iteration 3: log likelihood = -320.18821
Logit estimates Number of obs = 575
LR chi2(2) = 13.35
Prob > chi2 = 0.0013
Log likelihood = -320.18821 Pseudo R2 = 0.0204
------------------------------------------------------------------------------
dfree | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
ivhx2 | .6181526 .164247 -1.81 0.070 .3672198 1.040556
ivhx3 | .4607783 .0997937 -3.58 0.000 .301399 .7044372
------------------------------------------------------------------------------
lrtest, saving(4)
logit dfree
Iteration 0: log likelihood = -326.86446
Logit estimates Number of obs = 575
LR chi2(0) = -0.00
Prob > chi2 = .
Log likelihood = -326.86446 Pseudo R2 = -0.0000
------------------------------------------------------------------------------
dfree | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
_cons | -1.068691 .095599 -11.18 0.000 -1.256061 -.88132
------------------------------------------------------------------------------
lrtest, using(4)
Logit: likelihood-ratio test chi2(2) = 13.35
Prob > chi2 = 0.0013
logit dfree race
Iteration 0: log likelihood = -326.86446
Iteration 1: log likelihood = -324.56405
Iteration 2: log likelihood = -324.55269
Iteration 3: log likelihood = -324.55269
Logit estimates Number of obs = 575
LR chi2(1) = 4.62
Prob > chi2 = 0.0315
Log likelihood = -324.55269 Pseudo R2 = 0.0071
------------------------------------------------------------------------------
dfree | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
race | .4591026 .2109763 2.18 0.030 .0455967 .8726085
_cons | -1.193922 .1141504 -10.46 0.000 -1.417653 -.9701919
------------------------------------------------------------------------------
logit dfree race, or
Iteration 0: log likelihood = -326.86446
Iteration 1: log likelihood = -324.56405
Iteration 2: log likelihood = -324.55269
Iteration 3: log likelihood = -324.55269
Logit estimates Number of obs = 575
LR chi2(1) = 4.62
Prob > chi2 = 0.0315
Log likelihood = -324.55269 Pseudo R2 = 0.0071
------------------------------------------------------------------------------
dfree | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
race | 1.582653 .3339022 2.18 0.030 1.046652 2.393145
------------------------------------------------------------------------------
lrtest, saving(5)
logit dfree
Iteration 0: log likelihood = -326.86446
Logit estimates Number of obs = 575
LR chi2(0) = -0.00
Prob > chi2 = .
Log likelihood = -326.86446 Pseudo R2 = -0.0000
------------------------------------------------------------------------------
dfree | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
_cons | -1.068691 .095599 -11.18 0.000 -1.256061 -.88132
------------------------------------------------------------------------------
lrtest, using(5)
Logit: likelihood-ratio test chi2(1) = 4.62
Prob > chi2 = 0.0315
logit dfree treat
Iteration 0: log likelihood = -326.86446
Iteration 1: log likelihood = -324.28267
Iteration 2: log likelihood = -324.27534
Logit estimates Number of obs = 575
LR chi2(1) = 5.18
Prob > chi2 = 0.0229
Log likelihood = -324.27534 Pseudo R2 = 0.0079
------------------------------------------------------------------------------
dfree | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
treat | .437162 .1930633 2.26 0.024 .0587649 .8155591
_cons | -1.297816 .143296 -9.06 0.000 -1.578671 -1.016961
------------------------------------------------------------------------------
logit dfree treat, or
Iteration 0: log likelihood = -326.86446
Iteration 1: log likelihood = -324.28267
Iteration 2: log likelihood = -324.27534
Logit estimates Number of obs = 575
LR chi2(1) = 5.18
Prob > chi2 = 0.0229
Log likelihood = -324.27534 Pseudo R2 = 0.0079
------------------------------------------------------------------------------
dfree | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
treat | 1.548307 .2989212 2.26 0.024 1.060526 2.260439
------------------------------------------------------------------------------
lrtest, saving(6)
logit dfree
Iteration 0: log likelihood = -326.86446
Logit estimates Number of obs = 575
LR chi2(0) = -0.00
Prob > chi2 = .
Log likelihood = -326.86446 Pseudo R2 = -0.0000
------------------------------------------------------------------------------
dfree | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
_cons | -1.068691 .095599 -11.18 0.000 -1.256061 -.88132
------------------------------------------------------------------------------
lrtest, using(6)
Logit: likelihood-ratio test chi2(1) = 5.18
Prob > chi2 = 0.0229
logit dfree site
Iteration 0: log likelihood = -326.86446
Iteration 1: log likelihood = -326.0327
Iteration 2: log likelihood = -326.0315
Logit estimates Number of obs = 575
LR chi2(1) = 1.67
Prob > chi2 = 0.1968
Log likelihood = -326.0315 Pseudo R2 = 0.0025
------------------------------------------------------------------------------
dfree | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
site | .2642236 .2034167 1.30 0.194 -.1344658 .662913
_cons | -1.15268 .1170732 -9.85 0.000 -1.382139 -.9232202
------------------------------------------------------------------------------
logit dfree site, or
Iteration 0: log likelihood = -326.86446
Iteration 1: log likelihood = -326.0327
Iteration 2: log likelihood = -326.0315
Logit estimates Number of obs = 575
LR chi2(1) = 1.67
Prob > chi2 = 0.1968
Log likelihood = -326.0315 Pseudo R2 = 0.0025
------------------------------------------------------------------------------
dfree | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
site | 1.302419 .2649338 1.30 0.194 .8741828 1.940437
------------------------------------------------------------------------------
lrtest, saving(7)
logit dfree
Iteration 0: log likelihood = -326.86446
Logit estimates Number of obs = 575
LR chi2(0) = -0.00
Prob > chi2 = .
Log likelihood = -326.86446 Pseudo R2 = -0.0000
------------------------------------------------------------------------------
dfree | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
_cons | -1.068691 .095599 -11.18 0.000 -1.256061 -.88132
------------------------------------------------------------------------------
lrtest, using(7)
Logit: likelihood-ratio test chi2(1) = 1.67
Prob > chi2 = 0.1968
Table 4.2, page 106.
logit dfree age ndrugtx ivhx2 ivhx3 race treat site
Iteration 0: log likelihood = -326.86446
Iteration 1: log likelihood = -310.17928
Iteration 2: log likelihood = -309.62871
Iteration 3: log likelihood = -309.62413
Iteration 4: log likelihood = -309.62413
Logit estimates Number of obs = 575
LR chi2(7) = 34.48
Prob > chi2 = 0.0000
Log likelihood = -309.62413 Pseudo R2 = 0.0527
------------------------------------------------------------------------------
dfree | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
age | .0503708 .0173224 2.91 0.004 .0164196 .084322
ndrugtx | -.0615121 .0256311 -2.40 0.016 -.1117481 -.0112761
ivhx2 | -.6033296 .2872511 -2.10 0.036 -1.166331 -.0403278
ivhx3 | -.732722 .252329 -2.90 0.004 -1.227278 -.2381662
race | .2261295 .2233399 1.01 0.311 -.2116087 .6638677
treat | .4425031 .1992909 2.22 0.026 .0519002 .8331061
site | .1485845 .2172121 0.68 0.494 -.2771434 .5743125
_cons | -2.405405 .5548058 -4.34 0.000 -3.492805 -1.318006
------------------------------------------------------------------------------
Figure 4.2, page 107.
lowess dfree age, gen(var3) logit nodraw graph twoway line var3 age, sort xlabel(20(10)50 56)
Table 4.3, page 107.
sort age
generate age1 = (_n <= 148)
generate age2 = (_n >= 149) & (_n <= 292)
generate age3 = (_n >= 293) & (_n <= 458)
generate age4 = (_n >= 459)
logit dfree age2 age3 age4 ndrugtx ivhx2 ivhx3 race treat site
Iteration 0: log likelihood = -326.86446
Iteration 1: log likelihood = -310.10643
Iteration 2: log likelihood = -309.5257
Iteration 3: log likelihood = -309.52103
Iteration 4: log likelihood = -309.52103
Logit estimates Number of obs = 575
LR chi2(9) = 34.69
Prob > chi2 = 0.0001
Log likelihood = -309.52103 Pseudo R2 = 0.0531
------------------------------------------------------------------------------
dfree | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
age2 | -.165864 .2909137 -0.57 0.569 -.7360444 .4043163
age3 | .4693399 .27066 1.73 0.083 -.0611439 .9998237
age4 | .595771 .3124964 1.91 0.057 -.0167108 1.208253
ndrugtx | -.0587551 .0254688 -2.31 0.021 -.108673 -.0088371
ivhx2 | -.5545193 .2853626 -1.94 0.052 -1.11382 .0047811
ivhx3 | -.6725536 .2518601 -2.67 0.008 -1.16619 -.1789169
race | .2787172 .2238499 1.25 0.213 -.1600205 .7174549
treat | .4430577 .2000427 2.21 0.027 .0509812 .8351343
site | .1582001 .2188293 0.72 0.470 -.2706974 .5870976
_cons | -1.054837 .2705875 -3.90 0.000 -1.585179 -.5244956
------------------------------------------------------------------------------
Figure 4.3, page 108.
preserve clear input age coef 24 0 30.5 -.165864 35.5 .4693399 47.5 .595771 end graph twoway scatter coef age, connect(l) ylabel(-.25(.25).75) xlabel(20(10)50) yline(0)
restore
Table 4.4, page 109.
fracpoly logit dfree age ndrugtx ivhx2 ivhx3 race treat site, degree(2) compare
-> gen double Indru__1 = ndrugtx-4.543 if e(sample)
.......
-> gen double Iage__1 = X^-2-.0954 if e(sample)
-> gen double Iage__2 = X^3-33.96 if e(sample)
(where: X = age/10)
Logit estimates Number of obs = 575
LR chi2(8) = 34.96
Prob > chi2 = 0.0000
Log likelihood = -309.38436 Pseudo R2 = 0.0535
------------------------------------------------------------------------------
dfree | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
Iage__1 | -1.538626 4.575934 -0.34 0.737 -10.50729 7.43004
Iage__2 | .0116581 .0080977 1.44 0.150 -.0042132 .0275293
Indru__1 | -.0620596 .0257223 -2.41 0.016 -.1124744 -.0116447
ivhx2 | -.6057376 .2881578 -2.10 0.036 -1.170517 -.0409587
ivhx3 | -.7263554 .2525832 -2.88 0.004 -1.221409 -.2313014
race | .2282107 .224089 1.02 0.308 -.2109957 .6674171
treat | .4392589 .1996983 2.20 0.028 .0478573 .8306604
site | .1459101 .217491 0.67 0.502 -.2803644 .5721846
_cons | -1.082342 .2416317 -4.48 0.000 -1.555931 -.6087524
------------------------------------------------------------------------------
Deviance: 618.7687. Best powers of age among 44 models fit: -2 3.
Fractional polynomial model comparisons:
---------------------------------------------------------------
age df Deviance Gain P(term) Powers
---------------------------------------------------------------
Not in model 0 627.801 -- --
Linear 1 619.248 0.000 0.003 1
m = 1 2 618.882 0.366 0.545 3
m = 2 4 618.769 0.480 0.945 -2 3
---------------------------------------------------------------
Figure 4.4, page 110.
Thanks to Joe Hilbe for the Stata code.
lowess dfree ndrugtx, logit gen(low) sort ndrugtx twoway line low ndrugtx, ylabel(-1.9305 -.7306) xlabel(0 1 2 5(5)40)
Table 4.5, page 110.
gen group = .
(575 missing values generated)
replace group = 1 if ndrugtx==0
(79 real changes made)
replace group = 2 if ndrugtx==1 | ndrugtx==2
(173 real changes made)
replace group = 3 if ndrugtx>3 | ndrugtx<16
(575 real changes made)
replace group = 4 if ndrugtx>15
(29 real changes made)
xi: logit dfree age i.group ivhx2 ivhx3 race treat site
i.group _Igroup_3-4 (naturally coded; _Igroup_3 omitted)
Iteration 0: log likelihood = -326.86446
Iteration 1: log likelihood = -312.66548
Iteration 2: log likelihood = -312.41836
Iteration 3: log likelihood = -312.41801
Logit estimates Number of obs = 575
LR chi2(7) = 28.89
Prob > chi2 = 0.0002
Log likelihood = -312.41801 Pseudo R2 = 0.0442
------------------------------------------------------------------------------
dfree | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
age | .0456947 .0171201 2.67 0.008 .0121398 .0792496
_Igroup_4 | -.6099344 .5597557 -1.09 0.276 -1.707035 .4871667
ivhx2 | -.6801364 .2846812 -2.39 0.017 -1.238101 -.1221715
ivhx3 | -.864195 .2471705 -3.50 0.000 -1.34864 -.3797497
race | .2386873 .2230881 1.07 0.285 -.1985573 .6759319
treat | .4361921 .1983708 2.20 0.028 .0473925 .8249916
site | .1936553 .2152307 0.90 0.368 -.2281891 .6154997
_cons | -2.425773 .5525429 -4.39 0.000 -3.508738 -1.342809
------------------------------------------------------------------------------
Figure 4.5, page 111.
preserve clear input midpt coeff 0 0 1.5 .406 9 -.154 28 -.585 end graph twoway scatter coeff midpt, yline(0) connect(l) xlabel(0 1 2 5(5)20 28)
restore
Figure 4.6, page 112.
generate ndrgfp1 = ((ndrugtx+1)/10)^(-1) generate ndrgfp2 = ndrgfp1*log((ndrugtx+1)/10) generate lgtfp = -4.314 + 0.981*ndrgfp1 + 0.361*ndrgfp2 summarize lgtfp global mlgfp = r(mean) summarize low global mlow = r(mean) generate lgtfp1 = lgtfp + ($mlow-$mlgtfp) twoway (line low ndrugtx)(line lgtfp1 ndrugtx), ylabel(-2.184 -.547) xlabel(0 1 2 5(5)40)
Table 4.7, page 113.
logit dfree age ndrgfp1 ndrgfp2 ivhx2 ivhx3 race treat site
Iteration 0: log likelihood = -326.86446
Iteration 1: log likelihood = -307.22312
Iteration 2: log likelihood = -306.72663
Iteration 3: log likelihood = -306.72558
Logit estimates Number of obs = 575
LR chi2(8) = 40.28
Prob > chi2 = 0.0000
Log likelihood = -306.72558 Pseudo R2 = 0.0616
------------------------------------------------------------------------------
dfree | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
age | .0544455 .0174877 3.11 0.002 .0201703 .0887208
ndrgfp1 | .9814532 .2888474 3.40 0.001 .4153227 1.547584
ndrgfp2 | .3611252 .1098589 3.29 0.001 .1458057 .5764446
ivhx2 | -.6088269 .2911064 -2.09 0.036 -1.179385 -.0382689
ivhx3 | -.7238122 .2555643 -2.83 0.005 -1.224709 -.2229154
race | .2477026 .2242152 1.10 0.269 -.1917512 .6871564
treat | .4223666 .200365 2.11 0.035 .0296584 .8150748
site | .1732142 .2209758 0.78 0.433 -.2598905 .6063189
_cons | -4.313812 .7924526 -5.44 0.000 -5.866991 -2.760634
------------------------------------------------------------------------------
NOTE: Everything regarding the constant in this output is different from what is shown in the book, and we don't know why.
Table 4.9, page 115.
gen agendrgfp1 = age*ndrgfp1
gen racesite = race*site
logit dfree age ndrgfp1 ndrgfp2 ivhx2 ivhx3 race treat site agendrgfp1 racesite
Iteration 0: log likelihood = -326.86446
Iteration 1: log likelihood = -300.06724
Iteration 2: log likelihood = -298.98837
Iteration 3: log likelihood = -298.98146
Iteration 4: log likelihood = -298.98146
Logit estimates Number of obs = 575
LR chi2(10) = 55.77
Prob > chi2 = 0.0000
Log likelihood = -298.98146 Pseudo R2 = 0.0853
------------------------------------------------------------------------------
dfree | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
age | .1166385 .0288749 4.04 0.000 .0600446 .1732323
ndrgfp1 | 1.669035 .407152 4.10 0.000 .871032 2.467038
ndrgfp2 | .4336886 .1169052 3.71 0.000 .2045586 .6628185
ivhx2 | -.6346307 .2987192 -2.12 0.034 -1.220109 -.0491518
ivhx3 | -.7049475 .2615805 -2.69 0.007 -1.217636 -.1922591
race | .6841068 .2641355 2.59 0.010 .1664107 1.201803
treat | .4349255 .2037596 2.13 0.033 .035564 .834287
site | .516201 .2548881 2.03 0.043 .0166295 1.015773
agendrgfp1 | -.0152697 .0060268 -2.53 0.011 -.0270819 -.0034575
racesite | -1.429457 .5297806 -2.70 0.007 -2.467808 -.3911062
_cons | -6.843864 1.219316 -5.61 0.000 -9.23368 -4.454048
------------------------------------------------------------------------------
Table 4.11, page 123.
NOTE: G is calculated 'by hand' instead of using lrtest because it follows the book.
NOTE: The following code gives the log likelihood and the values for method 1.
logit dfree
Iteration 0: log likelihood = -326.86446
Logit estimates Number of obs = 575
LR chi2(0) = -0.00
Prob > chi2 = .
Log likelihood = -326.86446 Pseudo R2 = -0.0000
------------------------------------------------------------------------------
dfree | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
_cons | -1.068691 .095599 -11.18 0.000 -1.256061 -.88132
------------------------------------------------------------------------------
logit dfree ndrugtx
Iteration 0: log likelihood = -326.86446
Iteration 1: log likelihood = -321.33296
Iteration 2: log likelihood = -320.94874
Iteration 3: log likelihood = -320.94485
Iteration 4: log likelihood = -320.94485
Logit estimates Number of obs = 575
LR chi2(1) = 11.84
Prob > chi2 = 0.0006
Log likelihood = -320.94485 Pseudo R2 = 0.0181
------------------------------------------------------------------------------
dfree | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
ndrugtx | -.0749582 .024681 -3.04 0.002 -.123332 -.0265844
_cons | -.7677805 .130326 -5.89 0.000 -1.023215 -.5123462
------------------------------------------------------------------------------
display -2*(-326.864-(-320.945))
11.838
logit dfree ndrugtx treat
Iteration 0: log likelihood = -326.86446
Iteration 1: log likelihood = -318.82274
Iteration 2: log likelihood = -318.43381
Iteration 3: log likelihood = -318.42996
Iteration 4: log likelihood = -318.42995
Logit estimates Number of obs = 575
LR chi2(2) = 16.87
Prob > chi2 = 0.0002
Log likelihood = -318.42995 Pseudo R2 = 0.0258
------------------------------------------------------------------------------
dfree | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
ndrugtx | -.0739215 .0244703 -3.02 0.003 -.1218825 -.0259606
treat | .4347941 .1947802 2.23 0.026 .053032 .8165562
_cons | -.9990724 .1690772 -5.91 0.000 -1.330458 -.6676872
------------------------------------------------------------------------------
display -2*(-320.945-(-318.430))
5.03
logit dfree ndrugtx treat ivhx2 ivhx3
Iteration 0: log likelihood = -326.86446
Iteration 1: log likelihood = -315.36442
Iteration 2: log likelihood = -315.02739
Iteration 3: log likelihood = -315.02524
Iteration 4: log likelihood = -315.02524
Logit estimates Number of obs = 575
LR chi2(4) = 23.68
Prob > chi2 = 0.0001
Log likelihood = -315.02524 Pseudo R2 = 0.0362
------------------------------------------------------------------------------
dfree | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
ndrugtx | -.054248 .0246134 -2.20 0.028 -.1024895 -.0060066
treat | .4215337 .1965232 2.14 0.032 .0363553 .8067121
ivhx2 | -.4023913 .2710537 -1.48 0.138 -.9336468 .1288642
ivhx3 | -.5803755 .2289185 -2.54 0.011 -1.029047 -.1317036
_cons | -.7713421 .1877567 -4.11 0.000 -1.139339 -.4033457
------------------------------------------------------------------------------
display -2*(-318.430-(-315.025))
6.81
logit dfree ndrugtx treat ivhx2 ivhx3 age
Iteration 0: log likelihood = -326.86446
Iteration 1: log likelihood = -310.84391
Iteration 2: log likelihood = -310.29824
Iteration 3: log likelihood = -310.29344
Iteration 4: log likelihood = -310.29344
Logit estimates Number of obs = 575
LR chi2(5) = 33.14
Prob > chi2 = 0.0000
Log likelihood = -310.29344 Pseudo R2 = 0.0507
------------------------------------------------------------------------------
dfree | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
ndrugtx | -.0637598 .0256279 -2.49 0.013 -.1139896 -.01353
treat | .4513352 .1985966 2.27 0.023 .0620929 .8405774
ivhx2 | -.6236554 .2847028 -2.19 0.028 -1.181663 -.0656482
ivhx3 | -.8056123 .2445359 -3.29 0.001 -1.284894 -.3263307
age | .0525934 .0172105 3.06 0.002 .0188614 .0863254
_cons | -2.332764 .5483861 -4.25 0.000 -3.407581 -1.257947
------------------------------------------------------------------------------
display -2*(-315.025-(-310.293))
9.464
NOTE: The following code gives the values for method 2.
display -2*(-326.864-(-310.293)) 33.142 display -2*(-320.945-(-310.293)) 21.304 display -2*(-318.430-(-310.293)) 16.274 display -2*(-315.025-(-310.293)) 9.464
Table 4.12, page 126.
NOTE: We could not recreate this table.
Table 4.13, page 127.
NOTE: We could not recreate this table.
Table 4.14, page 133.
quietly logit dfree age beck ivhx2 ivhx3 ndrugtx race treat site
lrtest, saving(0)
quietly logit dfree age ivhx2 ivhx3 ndrugtx treat
lrtest, saving(1)
quietly logit dfree age ivhx2 ivhx3 ndrugtx race treat
lrtest, saving(2)
logit dfree age ivhx2 ivhx3 ndrugtx treat site
lrtest, saving(3)
quietly logit dfree age beck ivhx2 ivhx3 ndrugtx treat
lrtest, saving(4)
quietly logit dfree age ivhx3 ndrugtx treat
lrtest, saving(5)
lrtest, using(0) model(1)
Logit: likelihood-ratio test chi2(3) = 1.34
Prob > chi2 = 0.7198
lrtest, using(0) model(2)
Logit: likelihood-ratio test chi2(2) = 0.47
Prob > chi2 = 0.7922
lrtest, using(0) model(3)
Logit: likelihood-ratio test chi2(2) = 1.01
Prob > chi2 = 0.6021
lrtest, using(0) model(4)
Logit: likelihood-ratio test chi2(2) = 1.34
Prob > chi2 = 0.5119
lrtest, using(0) model(5)
Logit: likelihood-ratio test chi2(4) = 6.34
Prob > chi2 = 0.1751
Table 4.15, page 134.
NOTE: We were unable to recreate this table.
Table 4.16, page 137.
clear
input x y1 y2 y3 cnt
1 1 0 0 7
1 0 1 0 12
1 0 0 1 20
0 1 0 0 13
0 0 1 0 8
end
expand cnt
(55 observations created)
logistic x y1 y2 y3
note: y3~=0 predicts success perfectly
y3 dropped and 20 obs not used
note: y2 dropped due to collinearity
Logit estimates Number of obs = 40
LR chi2(1) = 2.53
Prob > chi2 = 0.1115
Log likelihood = -26.409166 Pseudo R2 = 0.0458
------------------------------------------------------------------------------
x | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
y1 | .3589744 .2348775 -1.57 0.117 .0995683 1.294213
------------------------------------------------------------------------------
NOTE: Stata is throwing out y3 and hence the results are different than those shown in the book. The point is that if you do not throw out y3, the odds ratios go to infinity, which is not correct.
Table 4.17, page 137.
clear input z x y cnt 1 1 1 5 1 1 0 5 1 0 1 2 1 0 0 8 2 1 1 10 2 1 0 2 2 0 1 2 2 0 0 6 3 1 1 15 3 0 1 1 3 0 0 4 end expand cnt (49 observations created)
Table 4.18, page 138. Results of fitting logistic regression models to the data in Table 4.17.
xi: logit y x i.z
i.z _Iz_1-3 (naturally coded; _Iz_1 omitted)
Iteration 0: log likelihood = -40.751596
Iteration 1: log likelihood = -27.598477
Iteration 2: log likelihood = -26.975899
Iteration 3: log likelihood = -26.956186
Iteration 4: log likelihood = -26.956153
Logit estimates Number of obs = 60
LR chi2(3) = 27.59
Prob > chi2 = 0.0000
Log likelihood = -26.956153 Pseudo R2 = 0.3385
------------------------------------------------------------------------------
y | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
x | 2.768072 .7156901 3.87 0.000 1.365345 4.170799
_Iz_2 | 1.188759 .8118658 1.46 0.143 -.4024691 2.779986
_Iz_3 | 2.038156 .8889852 2.29 0.022 .2957769 3.780535
_cons | -2.318938 .7727629 -3.00 0.003 -3.833526 -.8043506
------------------------------------------------------------------------------
xi: logit y i.z*x
i.z _Iz_1-3 (naturally coded; _Iz_1 omitted)
i.z*x _IzXx_# (coded as above)
note: _IzXx_3~=0 predicts success perfectly
_IzXx_3 dropped and 15 obs not used
Iteration 0: log likelihood = -30.913271
Iteration 1: log likelihood = -24.44454
Iteration 2: log likelihood = -24.343321
Iteration 3: log likelihood = -24.342924
Logit estimates Number of obs = 45
LR chi2(4) = 13.14
Prob > chi2 = 0.0106
Log likelihood = -24.342924 Pseudo R2 = 0.2125
------------------------------------------------------------------------------
y | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
_Iz_2 | .2876821 1.136512 0.25 0.800 -1.93984 2.515204
_Iz_3 | -1.36e-16 1.369298 -0.00 1.000 -2.683775 2.683775
x | 1.386294 1.012419 1.37 0.171 -.5980107 3.370599
_IzXx_2 | 1.321756 1.513806 0.87 0.383 -1.64525 4.288762
_cons | -1.386294 .7905647 -1.75 0.080 -2.935773 .163184
------------------------------------------------------------------------------
NOTE: See bolded output above. _IzXx_3~=0 predicts success perfectly; _IzXx_3 dropped and 15 obs not used. Because of the numerical problem with the empty cell, you need to use logexact or statexact.
Table 4.19, page 139.
clear
input x y
1 0
2 0
3 0
4 0
5 0
5.5 0
6 1
7 1
8 1
9 1
10 1
11 1
end
logit y x
outcome = x>5.5 predicts data perfectly
r(2000);
replace x = 6 in 6
(1 real change made)
logit y x
note: outcome = x>6 predicts data perfectly except for
x==6 subsample:
x dropped and 10 obs not used
Iteration 0: log likelihood = -1.3862944
Logit estimates Number of obs = 2
LR chi2(0) = 0.00
Prob > chi2 = .
Log likelihood = -1.3862944 Pseudo R2 = 0.0000
------------------------------------------------------------------------------
y | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
_cons | 0 1.414214 0.00 1.000 -2.771808 2.771808
------------------------------------------------------------------------------
replace x = 6.05 in 6
(1 real change made)
logit y x
Iteration 0: log likelihood = -8.3177662
Iteration 1: log likelihood = -3.5936372
Iteration 2: log likelihood = -2.5215663
Iteration 3: log likelihood = -1.9937606
Iteration 4: log likelihood = -1.7141988
Iteration 5: log likelihood = -1.5824089
Iteration 6: log likelihood = -1.5355823
Iteration 7: log likelihood = -1.5250977
Iteration 8: log likelihood = -1.5241422
Iteration 9: log likelihood = -1.5241292
Iteration 10: log likelihood = -1.5241292
Logit estimates Number of obs = 12
LR chi2(1) = 13.59
Prob > chi2 = 0.0002
Log likelihood = -1.5241292 Pseudo R2 = 0.8168
------------------------------------------------------------------------------
y | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
x | 4.345349 6.088002 0.71 0.475 -7.586917 16.27761
_cons | -26.17541 36.72909 -0.71 0.476 -98.16311 45.81229
------------------------------------------------------------------------------
note: 1 failure and 1 success completely determined.
replace x = 6.1 in 6
(1 real change made)
logit y x
Iteration 0: log likelihood = -8.3177662
Iteration 1: log likelihood = -3.6113685
Iteration 2: log likelihood = -2.5518515
Iteration 3: log likelihood = -2.0394264
Iteration 4: log likelihood = -1.7788149
Iteration 5: log likelihood = -1.6667265
Iteration 6: log likelihood = -1.6348295
Iteration 7: log likelihood = -1.6306873
Iteration 8: log likelihood = -1.6305766
Iteration 9: log likelihood = -1.6305765
Logit estimates Number of obs = 12
LR chi2(1) = 13.37
Prob > chi2 = 0.0003
Log likelihood = -1.6305765 Pseudo R2 = 0.8040
------------------------------------------------------------------------------
y | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
x | 3.635619 4.185012 0.87 0.385 -4.566853 11.83809
_cons | -21.97833 25.39863 -0.87 0.387 -71.75874 27.80207
------------------------------------------------------------------------------
note: 1 failure and 1 success completely determined.
replace x = 6.15 in 6
(1 real change made)
logit y x
Iteration 0: log likelihood = -8.3177662
Iteration 1: log likelihood = -3.6293154
Iteration 2: log likelihood = -2.5826053
Iteration 3: log likelihood = -2.0857308
Iteration 4: log likelihood = -1.8436308
Iteration 5: log likelihood = -1.7490886
Iteration 6: log likelihood = -1.7276365
Iteration 7: log likelihood = -1.7259834
Iteration 8: log likelihood = -1.7259691
Logit estimates Number of obs = 12
LR chi2(1) = 13.18
Prob > chi2 = 0.0003
Log likelihood = -1.7259691 Pseudo R2 = 0.7925
------------------------------------------------------------------------------
y | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
x | 3.220325 3.331755 0.97 0.334 -3.309796 9.750446
_cons | -19.5306 20.33991 -0.96 0.337 -59.39609 20.33488
------------------------------------------------------------------------------
replace x = 6.2 in 6
(1 real change made)
logit y x
Iteration 0: log likelihood = -8.3177662
Iteration 1: log likelihood = -3.6474741
Iteration 2: log likelihood = -2.6138084
Iteration 3: log likelihood = -2.1326014
Iteration 4: log likelihood = -1.9084543
Iteration 5: log likelihood = -1.8293235
Iteration 6: log likelihood = -1.815043
Iteration 7: log likelihood = -1.8143783
Iteration 8: log likelihood = -1.8143764
Logit estimates Number of obs = 12
LR chi2(1) = 13.01
Prob > chi2 = 0.0003
Log likelihood = -1.8143764 Pseudo R2 = 0.7819
------------------------------------------------------------------------------
y | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
x | 2.926873 2.817514 1.04 0.299 -2.595353 8.449099
_cons | -17.80292 17.29827 -1.03 0.303 -51.70691 16.10107
------------------------------------------------------------------------------
replace x = 8 in 6
(1 real change made)
logit y x
Iteration 0: log likelihood = -8.3177662
Iteration 1: log likelihood = -4.4070996
Iteration 2: log likelihood = -3.8715929
Iteration 3: log likelihood = -3.7841346
Iteration 4: log likelihood = -3.7799185
Iteration 5: log likelihood = -3.7799047
Logit estimates Number of obs = 12
LR chi2(1) = 9.08
Prob > chi2 = 0.0026
Log likelihood = -3.7799047 Pseudo R2 = 0.5456
------------------------------------------------------------------------------
y | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
x | .9664819 .5311971 1.82 0.069 -.0746452 2.007609
_cons | -6.123959 3.585271 -1.71 0.088 -13.15096 .9030426
------------------------------------------------------------------------------
Table 4.20, page 140.
clear
input subj x1 x2 x3 y
1 .225 .231 1.026 0
2 .487 .489 1.022 1
3 -1.080 -1.070 1.074 0
4 -.87 -.87 1.091 0
5 -.58 -.57 1.095 0
6 -.64 -.64 1.01 0
7 1.614 1.619 1.087 0
8 .352 .355 1.095 1
9 -1.025 -1.018 1.008 0
10 .929 .937 1.057 1
end
list subj x1 x2 x3 y
subj x1 x2 x3 y
1. 1 .225 .231 1.026 0
2. 2 .487 .489 1.022 1
3. 3 -1.08 -1.07 1.074 0
4. 4 -.87 -.87 1.091 0
5. 5 -.58 -.57 1.095 0
6. 6 -.64 -.64 1.01 0
7. 7 1.614 1.619 1.087 0
8. 8 .352 .355 1.095 1
9. 9 -1.025 -1.018 1.008 0
10. 10 .929 .937 1.057 1
Table 4.21, page 141.
Column 2
logit y x1
Iteration 0: log likelihood = -6.108643
Iteration 1: log likelihood = -4.9146936
Iteration 2: log likelihood = -4.8717399
Iteration 3: log likelihood = -4.8713285
Iteration 4: log likelihood = -4.8713284
Logit estimates Number of obs = 10
LR chi2(1) = 2.47
Prob > chi2 = 0.1157
Log likelihood = -4.8713284 Pseudo R2 = 0.2026
------------------------------------------------------------------------------
y | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
x1 | 1.380311 1.005368 1.37 0.170 -.5901735 3.350795
_cons | -1.001712 .8294342 -1.21 0.227 -2.627373 .6239494
------------------------------------------------------------------------------
Column 3 (Note that there is likely a typo in this column.)
logit y x1 x2
Iteration 0: log likelihood = -6.108643
Iteration 1: log likelihood = -4.8196088
Iteration 2: log likelihood = -4.7259858
Iteration 3: log likelihood = -4.7212724
Iteration 4: log likelihood = -4.721251
Logit estimates Number of obs = 10
LR chi2(2) = 2.77
Prob > chi2 = 0.2497
Log likelihood = -4.721251 Pseudo R2 = 0.2271
------------------------------------------------------------------------------
y | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
x1 | 146.395 276.9998 0.53 0.597 -396.5147 689.3047
x2 | -144.9098 276.6344 -0.52 0.600 -687.1033 397.2836
_cons | -.3703049 1.362457 -0.27 0.786 -3.040672 2.300062
------------------------------------------------------------------------------
Column 4 (Note that there is likely a typo in this column.)
logit y x3
Iteration 0: log likelihood = -6.108643
Iteration 1: log likelihood = -6.104626
Iteration 2: log likelihood = -6.1046254
Logit estimates Number of obs = 10
LR chi2(1) = 0.01
Prob > chi2 = 0.9286
Log likelihood = -6.1046254 Pseudo R2 = 0.0007
------------------------------------------------------------------------------
y | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
x3 | 1.787782 19.97092 0.09 0.929 -37.35449 40.93006
_cons | -2.736861 21.12781 -0.13 0.897 -44.1466 38.67288
------------------------------------------------------------------------------
Column 5
logit y x1 x2 x3
Iteration 0: log likelihood = -6.108643
Iteration 1: log likelihood = -4.8146158
Iteration 2: log likelihood = -4.7162391
Iteration 3: log likelihood = -4.71065
Iteration 4: log likelihood = -4.7106177
Logit estimates Number of obs = 10
LR chi2(3) = 2.80
Prob > chi2 = 0.4242
Log likelihood = -4.7106177 Pseudo R2 = 0.2289
------------------------------------------------------------------------------
y | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
x1 | 142.9769 282.1838 0.51 0.612 -410.0932 696.047
x2 | -141.4593 281.832 -0.50 0.616 -693.8398 410.9212
x3 | -3.621109 24.95384 -0.15 0.885 -52.52974 45.28752
_cons | 3.42313 26.1558 0.13 0.896 -47.8413 54.68756
------------------------------------------------------------------------------
UCLA Researchers are invited to our Statistical Consulting Services
We recommend others to our list of Other Resources for Statistical Computing Help
These pages are Copyrighted (c) by UCLA Academic Technology Services