Statalist The Stata Listserver


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: xtlogit vs gllamm


From   Bégin Karine <k.begin@umontreal.ca>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: xtlogit vs gllamm
Date   Mon, 15 May 2006 14:49:33 -0400

Hi,

 

I have a dichotomous outcome variable taken at various time points.  I performed a regression on this variable using both the "gllamm" command with a logit link, a binomial distribution and the adaptative quadrature (ado file) and the "xtlogit" command (running with the same number of adaptative quadrature points as with gllamm).  Both commands produce quiet different results and I am wondering why since both gllamm and xtlogit seem to be conceived for similar purpose.  An example of the results is listed below.

 

Thanks,

Karine

 

 

gllamm

 

. gllamm emploi sexe FAC3_, i(no_seque) link(logit) family(binom) nip(12) adapt

 

Running adaptive quadrature

Iteration 0:    log likelihood = -5998.8654

Iteration 1:    log likelihood = -3067.6979

Iteration 2:    log likelihood =  -2941.096

Iteration 3:    log likelihood = -3064.9737

Iteration 4:    log likelihood = -2937.5981

Iteration 5:    log likelihood = -2957.6985

Iteration 6:    log likelihood = -2969.5623

Iteration 7:    log likelihood = -3040.5152

Iteration 8:    log likelihood = -3040.4834

Iteration 9:    log likelihood = -3039.0249

Iteration 10:    log likelihood = -3037.5997

Iteration 11:    log likelihood = -3036.2361

Iteration 12:    log likelihood = -3035.5158

Iteration 13:    log likelihood = -3034.6755

Iteration 14:    log likelihood = -3034.3058

Iteration 15:    log likelihood = -3034.0816

Iteration 16:    log likelihood =  -3033.572

Iteration 17:    log likelihood = -3033.3959

Iteration 18:    log likelihood = -3032.6627

Iteration 19:    log likelihood =  -3032.346

Iteration 20:    log likelihood =  -3032.165

Iteration 21:    log likelihood =  -3032.041

Iteration 22:    log likelihood = -3031.9455

Iteration 23:    log likelihood = -3031.8731

Iteration 24:    log likelihood = -3031.8181

Iteration 25:    log likelihood = -3031.7767

Iteration 26:    log likelihood = -3031.7515

Iteration 27:    log likelihood = -3031.7283

Iteration 28:    log likelihood = -3031.7445

Iteration 29:    log likelihood = -3031.7501

Iteration 30:    log likelihood = -3031.7754

Iteration 31:    log likelihood = -3031.7591

Iteration 32:    log likelihood =  -3031.966

Iteration 33:    log likelihood = -3031.9902

Iteration 34:    log likelihood = -3031.9543

Iteration 35:    log likelihood = -3031.9529

 

 

Adaptive quadrature has converged, running Newton-Raphson

Iteration 0:   log likelihood = -2901.8159  

Iteration 1:   log likelihood = -2901.7724  

Iteration 2:   log likelihood =  -2901.772  

Iteration 3:   log likelihood =  -2901.772  

 

number of level 1 units = 12328

number of level 2 units = 1541

 

Condition Number = 8.8565296

 

gllamm model

 

log likelihood = -2901.772

 

------------------------------------------------------------------------------

      emploi |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]

-------------+----------------------------------------------------------------

        sexe |  -2.772054   .3028192    -9.15   0.000    -3.365569    -2.17854

       FAC3_ |   1.382007   .1186971    11.64   0.000     1.149365    1.614649

       _cons |  -9.172404   .4245712   -21.60   0.000    -10.00455    -8.34026

------------------------------------------------------------------------------

 

 

Variances and covariances of random effects

------------------------------------------------------------------------------

 

 

***level 2 (no_seque)

 

    var(1): 227.29026 (21.232383)

------------------------------------------------------------------------------

 

 

 

 

 

xtlogit

 

. xtlogit emploi sexe FAC3_, i(no_seque)

 

Fitting comparison model:

 

Iteration 0:   log likelihood = -7147.7101

Iteration 1:   log likelihood =  -7143.665

Iteration 2:   log likelihood =  -7143.664

 

Fitting full model:

 

tau =  0.0     log likelihood =  -7143.664

tau =  0.1     log likelihood = -6526.5334

tau =  0.2     log likelihood = -5998.8654

tau =  0.3     log likelihood = -5542.1559

tau =  0.4     log likelihood = -5136.8485

tau =  0.5     log likelihood = -4767.0482

tau =  0.6     log likelihood = -4419.9345

tau =  0.7     log likelihood = -4082.7112

tau =  0.8     log likelihood = -3736.9038

 

Iteration 0:   log likelihood =  -4084.348  

Iteration 1:   log likelihood = -3578.8779  

Iteration 2:   log likelihood = -3399.3091  

Iteration 3:   log likelihood = -3330.9429  

Iteration 4:   log likelihood = -3328.0047  

Iteration 5:   log likelihood = -3328.0046  

 

Random-effects logistic regression              Number of obs      =     12328

Group variable (i): no_seque                    Number of groups   =      1541

 

Random effects u_i ~ Gaussian                   Obs per group: min =         8

                                                               avg =       8.0

                                                               max =         8

 

                                                Wald chi2(2)       =     19.27

Log likelihood  = -3328.0046                    Prob > chi2        =    0.0001

 

------------------------------------------------------------------------------

      emploi |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]

-------------+----------------------------------------------------------------

        sexe |  -.1323433   .1503605    -0.88   0.379    -.4270445    .1623579

       FAC3_ |   .2813436    .065331     4.31   0.000     .1532971    .4093901

       _cons |  -2.290372    .085298   -26.85   0.000    -2.457553   -2.123191

-------------+----------------------------------------------------------------

    /lnsig2u |   2.481279   .0429478                      2.397103    2.565455

-------------+----------------------------------------------------------------

     sigma_u |   3.457824    .074253                       3.31531    3.606463

         rho |   .7842202   .0072676                      .7696356    .7981235

------------------------------------------------------------------------------

Likelihood-ratio test of rho=0: chibar2(01) =  7631.32 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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index