st: Re: question about ordering of independent variable entry during testing

["Martin Weiss" <martin.weiss1@gmx.de>]

Order does not matter once you have specified your dependent var in, 
say, -regress-. When Stata must allocate your input to different sets of 
covariates, as in -heckman-, the syntax diagram makes that clear in the help 
file. But within a varlist, order should not matter. If you are in doubt 
about that, try it on a simple example and see whether the results differ...

HTH
Martin
_______________________
----- Original Message ----- 
From: "Ian C Zink" <izink@rsmas.miami.edu>
To: <statalist@hsphsun2.harvard.edu>
Sent: Thursday, January 15, 2009 8:05 PM
Subject: st: question about ordering of independent variable entry during 
testing


> Hello statalisters,
>  My question regards the entry/order of listing of independent variables 
> in a variety of statistical tests (MANOVA, ANOVA, GLMs, regressions).  Is 
> there any difference in the order in which I place predictor variables 
> into the model, or does stata simply read all entered variables as equal? 
> Thank you,
> Ian
>
> --
> Ian C. Zink
> Aquaculture Department - Division of Marine Affairs U. of Miami - 
> Rosenstiel School of Marine and Atmospheric Science
> 4600 Rickenbacker Causeway
> Miami, FL 33149
> office: 305-421-4915
> fax: 305-421-4675
> email: izink@rsmas.miami.edu
>
> *
> *   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/