Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: Different results with Stata 10 and Stata 11

From   Maarten Buis <>
Subject   Re: st: Different results with Stata 10 and Stata 11
Date   Thu, 16 Jun 2011 19:33:17 +0200

On Thu, Jun 16, 2011 at 4:35 PM, Beatrice Crozza
<> wrote:
> What do you mean that -ml- changed? What is the result that I should
> consider correct?

-ml- is a program that tries to find the maximum of a function. It is
what Stata uses to find the maximum of the likelihood function. If
that maximum is hard to find that subtle changes to the algorithm can
make a big difference in whether or not that maximum is found.
Generally, I would be suspicious of any results where such subtleties
matter, but there are exceptions. Since you did not give us the
information I asked for I cannot be more specific than that.

-- Maarten

Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
*   For searches and help try:

© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index