On Nov 10, 2007 3:59 PM, Ziad El-Khatib <[email protected]> wrote:
> Hi Jay,
> Thank you for your prompt reply.
> i am trying to analyze the bi- and multi-variable log regression of
> risk factors to have viral failure (0: <400; 1. >400) using different
> variables, for example (0.adherence;1.non-adherent) etc..
>
> Any tips?
If you are just estimating log-normal regression, take the log and use
reg. You may also want to use the survival regression program, which
will do a lot of stuff for you automatically. You may want to be very
wary of log-normal errors when you have observations near 0---the
likelihood is quite unstable.
Jay
*
* 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/
