I believe that -ml- uses the mreldif function, which (according to the
rather old Stata 6 manual I have at home) looks at the maximum relative
difference between elements of two matrices:
max_{i,j}( ( |A[i,j] - B[i,j]| ) /( |B[i,j]| + 1 ) )
Where A and B are the matrices of coefficients
Hope this helps,
Maarten
--- Stas Kolenikov <[email protected]> wrote:
> Isn't it mentioned in the [ML] book? I'm used to thinking it is in
> the absolute values:
>
> d(x,y) = \sum_k |x_k-y_k|/( |x_k| + |y_k| )
>
> or something of that flavor.
>
> On 4/15/07, Lian <[email protected]> wrote:
> > I am doing a ml maximize and trying to find out how stata
> > calculates the "change" between the two coefficient vectors,
> > before comparing it to the "tolerance" to see if it can declare
> > convergence. My guess is that Stata calculates the euclidean
> > distance between the two coefficient vectors, but nowhere I could
> > find a confirmation to my guess.
-----------------------------------------
Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands
visiting address:
Buitenveldertselaan 3 (Metropolitan), room Z434
+31 20 5986715
http://home.fsw.vu.nl/m.buis/
-----------------------------------------
___________________________________________________________
Yahoo! Answers - Got a question? Someone out there knows the answer. Try it
now.
http://uk.answers.yahoo.com/
*
* 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/
