Re: st: SAS proc format and regression

[Nick Winter <nw53@cornell.edu>]

I'm not entirely clear on what is going on in your SAS syntax (a problem I 
have a lot with SAS syntax . . .), but I think you cannot do what you want 
without creating a new variable.

Certainly -label- is not the tool for the job--it only deals with the names 
attached to the underlying values of a variable, and is irrelevant to 
estimation commands.

Why not do this:

        generate byte schoolhi = school>=12 if school<.
        logistic y schoolhi

I'll note that this takes two lines of code, compared with the 8 in SAS.

--Nick Winter


At 12:22 PM 7/8/2004 -0400, you wrote:

> Hi,
> In SAS, we can use proc format to change label value, for example, school 
> is the years of schooling, which ranges 0 to 17. We can use:
> proc format;
> value school low-<12='<12' 12-high='12+';
> run;
> later in regression we can use the format so that school is inlucded as a 
> dummy variable:
> proc logistic;
> class school;
> model y=school;
> format school school.;
> run;
> How do we achieve the same goal in Stata without creating new variables? I 
> thought we could use label define and label value, but it didn't work.
> Thanks a lot,
>
> Zhehui
>
> *
> *   For searches and help try:
> *   http://www.stata.com/support/faqs/res/findit.html
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/
--------------------------------------------------------
Nicholas Winter                           607.255.8819 t
Assistant Professor                       607.255.4530 f
Department of Government              nw53@cornell.edu e
308 White Hall            falcon.arts.cornell.edu/nw53 w
Cornell University
Ithaca, NY 14853-4601 

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/