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: Can multicollinearity problems be resolved by using residuals from another regression?


From   Maarten Buis <maartenlbuis@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Can multicollinearity problems be resolved by using residuals from another regression?
Date   Sat, 10 Nov 2012 14:24:15 +0100

On Fri, Nov 9, 2012 at 7:42 PM, Anat (Manes) Tchetchik
<anatmanes@gmail.com> wrote:
> What is the  correlation between x1 and x2?
> Plugging residuals from the regression of x2 in x1 should address
> problem of collinearity (though I think you should run equation (2)
> without constant.

That makes no sense to me: you added x2 because you think it is
correlated with x1, otherwise you would not need to control for x2.
Taking the correlation between x1 and x2 out of the model defeats the
very purpose of trying to control for x2.

-- Maarten

---------------------------------
Maarten L. Buis
WZB
Reichpietschufer 50
10785 Berlin
Germany

http://www.maartenbuis.nl
---------------------------------
*
*   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