Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: RE: qreg does not converge
From
"Nick Cox" <[email protected]>
To
<[email protected]>
Subject
st: RE: qreg does not converge
Date
Tue, 16 Mar 2010 20:15:15 -0000
In addition to earlier comments, this all sounds as if you really want
to force Stata to fit a model that it is finding intensely problematic.
I don't think that's usually a very good idea. You may need to revisit
some assumptions. For example are there outliers? Is the general idea of
a hyperplane summary scientifically reasonable in view of what you know?
(For "science" read "economics", or whatever fits.)
Nick
[email protected]
Jen Zhen
To add one thing to my previous question:
We also have the problem that the estimates do not converge and we get
no estimate at all, unless we cut the number of observations by 50%,
which is a shame because it costs us statistical significance.
Is there maybe something we can do to still have it converge even on
the larger sample?
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/