st: Pearson's X2 for binomial logistic regression models

[Maurizio Pisati <maurizio.pisati@galactica.it>]

Dear Statalisters,
suppose I want to compute Pearson's X2 after a binomial logistic regression 
model. Stata offers me two ways to do it:

1) glm y x1 x2 x3, family(binomial)

2) logit y x1 x2 x3
   lfit

Sometimes - i.e., when the number of covariate patterns M equals the number 
of observations N - the two measures are the same, but other times - i.e., 
when M<N - the two measures differ. In the latter case, should I rely on 
the Pearson's X2 computed by -glm- or on the one computed by -lfit-?
Thank you for any help and best regards,
Maurizio Pisati





<><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><>
 Maurizio Pisati
 Associate Professor
 Department of Sociology and Social Research
 University of Milano Bicocca
 Edificio U7
 Via Bicocca degli Arcimboldi, 9
 20126 Milano MI
 Italy
 Tel: +39-02-64487533
 Fax: +39-02-64487561
 E-mail: maurizio.pisati@galactica.it
<><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><>

*
*   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/