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

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

<>
Lisa wrote

As suggested by Kit, I z-transformed my independent and dependent variables. I used the command

.center varlist, standardize

Now my R^2 and F value go down. How can that happen, I have learned that R^2 and F value don't change if you z-transform.

If I ran a regular OLS instead of a Prais-Winsten regression, R^2 and F value don't change. So I guess, it has something to do with the Prais-Winsten regression. Does anybody know the reason?



webuse lutkepohl,clear
center consumption income qtr, standardize
reg consumption income qtr
reg consumption income qtr, beta
// note that SEs, F change when you est on z-transformed vars
// as opposed to merely asking for beta coefficients on the regular regression
reg c_consumption c_income c_qtr, nocons

prais consumption income qtr, twostep
// likewise, SEs, F change when you est on z-transformed vars
// r^2 changes as well
prais c_consumption c_income c_qtr, noconst twostep

Kit



Kit Baum   |   Boston College Economics and 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/