re: st: RE: Re: standardized betas in Prais-Winsten Regression

[Christopher Baum <kit.baum@bc.edu>]

<.>
Lisa said

I centered all my variables and ran the Prais-Winsten Regression with the centered variables. The coefficients are the same for uncentered and centered variables. I think that this can't be true. Does anyone know why this problem occurs?


Actually if you want beta coefficients, you want to not only center them but z-transform them, that is, subtract the mean and divide by the sd. Subtracting constants from y and x doesn't change their correlation.

But z-transforming is a linear transformation, and regression of a lin.transf.(y) on a lin.transf.(x) doesn't change r^2. F, t-stats, etc. So why should this be surprising?

Kit

Kit Baum   |   Boston College Economics & DIW Berlin   |   http://ideas.repec.org/e/pba1.html
                              An Introduction to Stata Programming  |   http://www.stata-press.com/books/isp.html
   An Introduction to Modern Econometrics Using Stata  |   http://www.stata-press.com/books/imeus.html


*
*   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/