# Re: st: running gllamm in stata

 From Timothy.Mak@iop.kcl.ac.uk To statalist@hsphsun2.harvard.edu Subject Re: st: running gllamm in stata Date Fri, 9 Jun 2006 10:23:16 +0100

```Hi Sharad,

gllamm is known for its slowness. I seem to remember that there was once a
analyses for you in a supercomputer. I can't find it since. Maybe it is no
longer available.

Another issue is: you probably reduced your number of integration points
to 5 to save time, but are you sure it's sufficient for your purpose?

Hope that helps.
Tim

09/06/2006 09:33
statalist@hsphsun2.harvard.edu

To
statalist@hsphsun2.harvard.edu
cc

Subject
st: running gllamm in stata

Hello,
Based on the GLLAMM manual I tried to run two level
random coefficient model for binary outcome variable.
It took about 4 hour to run the model. I suspect I
could not input the comands correctly. I am also not
clear about  defining matrix, equation and other
options. May I request for your help? Data source,
variables and syntax which I used are as follows,
Data source is women nested within village (average
women per village is 10, minimum4 maximum 80). There
are 2 level2 variables and 6 level1 variables, with
n=1060
Level 2 (village) variables: vi24 vi26
Level 1 (women)  variables: svcompr (dependent with 1
yes and 0 no), bpod, anctrain, ddiff, crillnes,
delhist, alcohol
Input comands were as follows,
. gen cons=1
. eq inter: cons
. eq slope: anctrain alcohol crillnes delhist
. matrix a = e(b)
. matrix a = (a, .2, 0)
. gllamm svcompr anctrain alcohol crillnes delhist
vi24 vi26, i(vill) link(logit) family(binom) nrf(2)
eqs(inter slope) nip(5) copy adapt eform
My questions are, whether the comand is correst? if
so, how can the computer be made to run comand faster?
If it is not correct, what would be the correct
comand.
Hoping appropriate suggestions,
Sincerely

__________________________________________________
Do You Yahoo!?
Tired of spam?  Yahoo! Mail has the best spam protection around
http://mail.yahoo.com
*
*   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/

*
*   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/
```