Dear Stata-L,
We're stumped!
Here's the situation. We used the same program for logistic regression,
same version of STATA (v11, which was never updated since July '09), and
same data. We get the same means, standard deviation, coefficients,
standard errors, significance levels, odds-ratios and R^2, BUT we get a
different Model Constant and Log-likelihood figures. Both figures are
larger by about a factor of five from the original run of the model in
September '09. Any ideas about what would cause these two things to be
different??
Thanks for your help!
-- Florio
*
* 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/
