--- Alberto R. Osella wrote:
> I'm trying to fit a GLLAMM to data <snip> but there are
> problems with the convergence.
Could be many things. One thing that struck me was the
line: -gen lvita = log(vita+0.001)- in your code. This
can very easily turn your zeros in big outliers, which
can cause trouble with convergence. For example in the
example code below you can see that the zeros are put
way outside the normal range of the data.
*----------- begin example -------------
sysuse nlsw88, clear
gen ln_tenure = ln(tenure + .001)
spikeplot ln_tenure
*------------ end example --------------
Hope this helps,
Maarten
PS. formatted text (rich text, xml, html) don't format
well on the list. Your message looks for example like: <http://www.hsph.harvard.edu/cgi-bin/lwgate/STATALIST/
archives/statalist.1002/date/article-721.html> For that
reason the Statalist FAQ askes everyone to post their
messages as plain text. See number of 4 of:
<http://www.stata.com/support/faqs/res/statalist.html#toask>
--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany
http://www.maartenbuis.nl
--------------------------
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
