Statalist


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

Re: st: multicollinearity


From   SR Millis <srmillis@yahoo.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: multicollinearity
Date   Thu, 20 Nov 2008 17:07:47 -0800 (PST)

VIF alone is not sufficient to evaluate the degree and source of collinearity.  You also need to examine the condition indexes and the variance decomposition proportions.

SR Millis



--- On Thu, 11/20/08, Chris Witte <eljefespeaks@yahoo.com> wrote:

> From: Chris Witte <eljefespeaks@yahoo.com>
> Subject: Re: st: multicollinearity
> To: statalist@hsphsun2.harvard.edu
> Date: Thursday, November 20, 2008, 4:00 PM
> Thanks for the advice Jay.
> 
> Regarding the listserv:  I remembered not being able to
> post in the past because I was trying to send rich text and
> I thought that maybe sending a link was unacceptable as
> well.  I usually stay pretty calm when I don't
> instantly see my question posted.
> 
> Regarding variance inflation factors:  I just tried out
> the -collin- function for fun.  Is there a generally
> accepted VIF value that should raise a red flag?... Or is
> this something that people argue about too?  I seem to
> recall that VIF's above 10 are supposed to be bad,
> right? 
> 


*
*   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/



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