Re: st: Multicollinearity in slogit

[SR Millis <aa3379@wayne.edu>]

The issue of collinearity concerns the relationships among the covariates (or independent variables).  Thus, the functional form of the model for the response variable is irrelevant to the estimation of collinearity.  In your model, you can assess the degree of collinearity by the standard diagnostics: condition indexes, variance decomposition proportions, and VIFs.

Scott Millis



--- On Mon, 7/19/10, Maarten buis <maartenbuis@yahoo.co.uk> wrote:

> From: Maarten buis <maartenbuis@yahoo.co.uk>
> Subject: Re: st: Multicollinearity in slogit
> To: statalist@hsphsun2.harvard.edu
> Date: Monday, July 19, 2010, 11:48 AM
> --- On Mon, 19/7/10, Abdul Salam
> Lodhi wrote:
> >  any one if know how to check for
> multicollinearity in
> > slogit model.
> 
> Just use -corr- to look at the correlations between the
> explanatory variables. Remember that multicollinearity
> is never a problem. See, e.g.
> <http://www.stata.com/statalist/archive/2010-02/msg00290.html>
> or
> <http://www.stata.com/statalist/archive/2010-07/msg00675.html>
> 
> Hope this helps,
> Maarten
> 
> --------------------------
> Maarten L. Buis
> Institut fuer Soziologie
> Universitaet Tuebingen
> Wilhelmstrasse 36
> 72074 Tuebingen
> Germany
> 
> http://www.maartenbuis.nl
> --------------------------
> 
> 
>       
> 
> *
> *   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/
> 

*
*   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/