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]
Re: st: asclogit not converging
From
"JVerkuilen (Gmail)" <[email protected]>
To
[email protected]
Subject
Re: st: asclogit not converging
Date
Tue, 19 Feb 2013 11:34:23 -0500
On Tue, Feb 19, 2013 at 10:24 AM, Jacobs, David
<[email protected]> wrote:
> One possible culprit that you might not have already checked concerns disparities in the range of explanatory variables.
>
> If you have a variable like U.S. city population, which may run from (say) 25,000 to almost 9 million, divide that variable by 10,000 or 100,000 or whatever it takes to get the variable in question down to a range like that of the rest of the variables in your model. I find this simple trick often works when zero inflated or other count models won't converge.
>
> It may work for your models.
Beyond a linear change of scale, a transformation like taking the log
may also be in order when you have variables like that, because NYC at
9 million will be a HUGE leverage point, and categorical data models
are affected by leverage points. Yes New Yorkers are a bunch of
self-centered jerks who don't acknowledge the rest of the universe but
that doesn't mean your model should follow suit.
(Note: I live there. ;)
Jay
*
* 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/