|
|  |
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: xtlogit RE on Stata 7 vs Stata 9
Hello,
I have a dataset and run xtlogit with RE in Stata 9. Then I save the
data as a Stata7 dataset using saveold and run xtlogit with RE under
Stata 7. The two xtlogit results differ.
The two data summaries are identical in Stata 7 and Stata 9. The
results of a simple logit (without xt) are also identical.
My questions are:
(1) why do the results differ and
(2) can I obtain the Stata 9 results with the Stata 7 software?
Below is the output. Thanks a lot for any help with this.
Regina Riphahn
---------------------------------------------------
Stata 7:
. xtlogit prezu age2-age11 yy2-yy14 elig_f62_01 elig_f62_05
elig_f63_05, i(id) re
Fitting comparison model:
Iteration 0: log likelihood = -3121.3503
Iteration 1: log likelihood = -2906.8883
Iteration 2: log likelihood = -2891.8834
Iteration 3: log likelihood = -2891.5045
Iteration 4: log likelihood = -2891.504
Fitting full model:
rho = 0.0 log likelihood = -2891.504
rho = 0.1 log likelihood = -2883.3786
rho = 0.2 log likelihood = -2875.0468
rho = 0.3 log likelihood = -2866.7138
rho = 0.4 log likelihood = -2858.7989
rho = 0.5 log likelihood = -2852.1705
rho = 0.6 log likelihood = -2848.7027
rho = 0.7 log likelihood = -2852.7707
Iteration 0: log likelihood = -2848.7027
Iteration 1: log likelihood = -2818.6218
Iteration 2: log likelihood = -2810.6961
Iteration 3: log likelihood = -2809.6725
Iteration 4: log likelihood = -2809.636
Iteration 5: log likelihood = -2809.636
Random-effects logit Number of obs = 5910
Group variable (i) : id Number of groups = 3222
Random effects u_i ~ Gaussian Obs per group: min = 1
avg = 1.8
max = 5
Wald chi2(26) = 196.37
Log likelihood = -2809.636 Prob > chi2 = 0.0000
------------------------------------------------------------------------------
prezu | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
age2 | 3.646622 .3009621 12.12 0.000 3.056747 4.236497
age3 | 3.633715 .3125701 11.63 0.000 3.021088 4.246341
age4 | 3.21058 .3274407 9.81 0.000 2.568808 3.852352
age5 | 3.653281 .3500519 10.44 0.000 2.967192 4.33937
age6 | 3.413544 .3519773 9.70 0.000 2.723681 4.103407
age7 | 3.432608 .3723435 9.22 0.000 2.702828 4.162388
age8 | 3.850869 .3863218 9.97 0.000 3.093693 4.608046
age9 | 3.837278 .4093726 9.37 0.000 3.034922 4.639633
age10 | 4.30106 .4242982 10.14 0.000 3.469451 5.13267
age11 | 3.933643 .4525593 8.69 0.000 3.046643 4.820642
yy2 | -.0700118 .3087082 -0.23 0.821 -.6750687 .5350451
yy3 | -.2210668 .3275647 -0.67 0.500 -.8630818 .4209483
yy4 | .2467167 .3438844 0.72 0.473 -.4272843 .9207177
yy5 | -.431473 .3582114 -1.20 0.228 -1.133554 .2706084
yy6 | .2021361 .3521311 0.57 0.566 -.4880281 .8923003
yy7 | -.1854823 .3590045 -0.52 0.605 -.8891182 .5181535
yy8 | .0121665 .3516642 0.03 0.972 -.6770827 .7014157
yy9 | -.3304559 .3601846 -0.92 0.359 -1.036405 .3754929
yy10 | .1540463 .359528 0.43 0.668 -.5506155 .8587082
yy11 | -.0394188 .3457641 -0.11 0.909 -.717104 .6382664
yy12 | .5164186 .3073526 1.68 0.093 -.0859815 1.118819
yy13 | .4452438 .3066294 1.45 0.146 -.1557389 1.046226
yy14 | .4991963 .3356244 1.49 0.137 -.1586154 1.157008
elig_f62_01 | -2.260383 .2928972 -7.72 0.000 -2.834451 -1.686315
elig_f62_05 | -3.09641 .4480864 -6.91 0.000 -3.974643 -2.218177
elig_f63_05 | -.7504618 .3648543 -2.06 0.040 -1.465563 -.0353606
_cons | -4.624642 .4351144 -10.63 0.000 -5.47745 -3.771833
-------------+----------------------------------------------------------------
/lnsig2u | 1.73885 .1756989 1.394487 2.083214
-------------+----------------------------------------------------------------
sigma_u | 2.385539 .2095683 2.008209 2.833767
rho | .850541 .022335 .8013075 .8892609
------------------------------------------------------------------------------
Likelihood ratio test of rho=0: chibar2(01) = 163.74 Prob >= chibar2 = 0.000
---------------------------------------------------
Stata 9:
. xtlogit prezu age2-age11 yy2-yy14 elig_f62_01 elig_f62_05
elig_f63_05, i(id) re
Fitting comparison model:
Iteration 0: log likelihood = -3121.3503
Iteration 1: log likelihood = -2906.8883
Iteration 2: log likelihood = -2891.8834
Iteration 3: log likelihood = -2891.5045
Iteration 4: log likelihood = -2891.504
Fitting full model:
tau = 0.0 log likelihood = -2891.504
tau = 0.1 log likelihood = -2883.3786
tau = 0.2 log likelihood = -2875.0468
tau = 0.3 log likelihood = -2866.7138
tau = 0.4 log likelihood = -2858.7989
tau = 0.5 log likelihood = -2852.1705
tau = 0.6 log likelihood = -2848.7027
tau = 0.7 log likelihood = -2852.7707
Iteration 0: log likelihood = -2848.7671
Iteration 1: log likelihood = -2827.9009
Iteration 2: log likelihood = -2822.6082
Iteration 3: log likelihood = -2822.5381
Iteration 4: log likelihood = -2822.5381
Random-effects logistic regression Number of obs = 5910
Group variable (i): id Number of groups = 3222
Random effects u_i ~ Gaussian Obs per group: min = 1
avg = 1.8
max = 5
Wald chi2(26) = 373.00
Log likelihood = -2822.5381 Prob > chi2 = 0.0000
------------------------------------------------------------------------------
prezu | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
age2 | 2.941085 .1999798 14.71 0.000 2.549132 3.333038
age3 | 2.802831 .1906641 14.70 0.000 2.429136 3.176526
age4 | 2.374153 .2026206 11.72 0.000 1.977024 2.771282
age5 | 2.731445 .2096436 13.03 0.000 2.320551 3.142338
age6 | 2.547736 .2219622 11.48 0.000 2.112698 2.982774
age7 | 2.516215 .2350732 10.70 0.000 2.05548 2.97695
age8 | 2.869614 .2346367 12.23 0.000 2.409734 3.329493
age9 | 2.842631 .255921 11.11 0.000 2.341035 3.344227
age10 | 3.258036 .2612136 12.47 0.000 2.746067 3.770005
age11 | 2.875536 .2815434 10.21 0.000 2.323721 3.427351
yy2 | -.1901037 .2619313 -0.73 0.468 -.7034796 .3232723
yy3 | -.3360713 .2729222 -1.23 0.218 -.8709891 .1988464
yy4 | -.0166281 .2808143 -0.06 0.953 -.567014 .5337579
yy5 | -.5925466 .2955848 -2.00 0.045 -1.171882 -.013211
yy6 | -.0325841 .2865391 -0.11 0.909 -.5941905 .5290223
yy7 | -.3331399 .2950807 -1.13 0.259 -.9114875 .2452077
yy8 | -.177989 .2868812 -0.62 0.535 -.7402658 .3842877
yy9 | -.4620822 .2966164 -1.56 0.119 -1.04344 .1192752
yy10 | -.0246008 .294431 -0.08 0.933 -.6016748 .5524733
yy11 | -.1293543 .2849911 -0.45 0.650 -.6879266 .4292179
yy12 | .3612259 .2475996 1.46 0.145 -.1240604 .8465123
yy13 | .1970864 .2425833 0.81 0.417 -.2783681 .672541
yy14 | .1549093 .2612761 0.59 0.553 -.3571824 .667001
elig_f62_01 | -1.891189 .233818 -8.09 0.000 -2.349464 -1.432914
elig_f62_05 | -2.51271 .3540054 -7.10 0.000 -3.206548 -1.818873
elig_f63_05 | -.5418482 .3037068 -1.78 0.074 -1.137103 .0534061
_cons | -3.548111 .2619457 -13.55 0.000 -4.061516 -3.034707
-------------+----------------------------------------------------------------
/lnsig2u | .9345126 .0912586 .755649 1.113376
-------------+----------------------------------------------------------------
sigma_u | 1.59561 .0728066 1.459107 1.744884
rho | .4362649 .0224439 .3928857 .4806419
------------------------------------------------------------------------------
Likelihood-ratio test of rho=0: chibar2(01) = 137.93 Prob >= chibar2 = 0.000
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
