It's my impression that Stata programmers,
including users, often stop
short of implementing support for pweights.
It sometimes seems that that would need
to follow someone working out the theory
first!
Be that as it may, whatever is in the public
domain should be locatable via a -findit- with
appropriate keywords.
Nick
[email protected]
Leslie-Anne Keown
> I realize that I can use fitstat to get some information on
> fit. However, I
> would like to go beyond just presenting BIC or Pseudo-R2 d
> report the area
> under the curve etc. that is obtained using lfit, lroc and
> lstat. However,
> none of these will run after pweighted models. Thus, I am left with my
> original questions.
> >I have been estimating logistic models with pweights on
> large Stats Canada
> >surveys. Unfortunately, lfit, lstat, lroc etc. will not run after
> >estimating a logistic regression with pweights. It does not
> seem like it
> >would be particularly difficult to calculate these
> statistics after running
> >a logistic with pweights. This leaves me wondering if there is some
> >particular reasoning that I am missing as to why these
> commands will not
> >run
> >after pweighted models. My question is two-fold:
> >1) is there a particular reason why these commands will not run after
> >pweighted models?
> >And
> >2) if there is not, are there any downloads possible that
> will allow these
> >commands to be used after pweighted models?
*
* 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/
