Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


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

Re: st: non-linear models not converging


From   "JVerkuilen (Gmail)" <jvverkuilen@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: non-linear models not converging
Date   Wed, 22 May 2013 13:53:00 -0400

On Wed, May 22, 2013 at 12:41 PM, Jacobs, David
<jacobs.184@sociology.osu.edu> wrote:
> Another quite simple but nevertheless useful technique:  Make sure that you don't have extremely large differences in the values of your explanatory variables.   For example, I've had this problem in count models when I enter state populations in their raw form along additional explanatory variables that were much smaller such as proportions or percentages.
>
> If this difficulty is present, multiply your original variable by .001 or .0001 or some such and try that remedy.

As good as the QR algorithm is a truly poor choice of scaling is going
to cause problems. It's generally good practice to scale your X
variables yourself to be on roughly the same order of magnitude. The
more complex the model the more this seems necessary.


-- 
JVVerkuilen, PhD
jvverkuilen@gmail.com

"They were careless people, Tom and Daisy - they smashed up things and
creatures and then retreated back into their money of their vast
carelessness, or whatever it was that kept them together, and let
other people clean up the mess they had made." -- F. Scott Fitzgerald

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index