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: VIF and binary predictors?
From
Pavel Roshanov <[email protected]>
To
[email protected]
Subject
Re: st: VIF and binary predictors?
Date
Sat, 6 Aug 2011 10:32:03 -0400
Dear Richard,
I have been using -collin- but all of the measures there are similar
to the VIF: R^2 and tolerance (which is just 1-R^2). It's the validity
of R^2 for binary variables that worries me.
Pavel
On Fri, Aug 5, 2011 at 11:57 PM, Richard Williams
<[email protected]> wrote:
> At 09:41 PM 8/5/2011, Pavel Roshanov wrote:
>>
>> Dear Statalist,
>>
>> I'm trying to detect multicollinearity in a dataset with binary
>> predictors. I have suggestions that VIF works just fine in this
>> situation but when I see the formula VIF=1/(1-R^2) I am not convinced.
>> Does anyone have any insight here?
>
> I am not sure why you are not convinced, but if you want a few more measures
> try Phil Ender's -collin- command, available from the UCLA site.
>
>
> -------------------------------------------
> Richard Williams, Notre Dame Dept of Sociology
> OFFICE: (574)631-6668, (574)631-6463
> HOME: (574)289-5227
> EMAIL: [email protected]
> WWW: http://www.nd.edu/~rwilliam
>
> *
> * 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/