I've found that believing that my model
is good doesn't make the estimation converge.
You might try stripping it down to see what
does work.
Nick
[email protected]
Rachel
> Thanks for your response. This was also what I thought initially. I've
> rechecked my model several times, and as far as I know, it should
> converge (at least locally, given the right starting point). So
> there's no more I can do on that point.
>
> On 12/20/06, Nick Cox <[email protected]> wrote:
> > The answer to the first question is No. If this
> > were compulsory, Stata would have no problem
> > in detecting any deficiency and throwing you out of -ml-.
> >
> > Without more detail, even an -ml- expert (not me)
> > might have difficulty advising here, but a guess
> > is that your problem is much more likely
> > to be with the model you are trying to estimate --
> > you may be trying to fit an elephant to an oak
> > tree -- than with variable types.
> >
*
* 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/
