Bookmark and Share

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: mean centering


From   Jvverkuilen <jvverkuilen@gmail.com>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   Re: st: mean centering
Date   Sun, 20 Jan 2013 19:01:48 -0500

Yes, from what I recall from scientific computing, the QR decomposition solves the numerical problems. It effectively centers and orthogonalizes the variables. 

Centering is really about interpretation now. 

--
JVerkuilen, PhD

Sent from my iPhone. 

"Out beyond ideas of wrong-doing and right-doing there is a field. I'll meet you there. When the soul lies down in that grass the world is too full to talk about." ---Rumi

On Jan 20, 2013, at 18:46, "Airey, David C" <david.airey@vanderbilt.edu> wrote:

> .
> 
>> Yes, and it's not bad practice most of the time. 
> 
> I picked up in a recent discussion that mean centering used to be a remedy for computational problems related to collinearity, like when you square or cube continuous variables to allow nonlinearity in regression models. However, modern methods like Q-R decomposition makes this an unnecessary concern and today mean centering helps with interpretation only if that.
> 
> Anyone agree with this?
> 
> -Dave
> 
> *
> *   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/

*
*   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 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index