Date:         Wed, 3 Aug 2005 18:49:15 -0300
Reply-To:     Hector Maletta <hmaletta@fibertel.com.ar>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         Hector Maletta <hmaletta@fibertel.com.ar>
Subject:      Re: Reference Category for Categorical Vars in NOMREG
Comments: To: Marc Scoppettone <mscoppettone@IAGR.NET>
In-Reply-To:  <200508032144.j73LiLo3020815@listserv.cc.uga.edu>
Content-Type: text/plain; charset="iso-8859-1"

With the dependent (multi-category) variable you can choose one category as
the reference (default is the last, but you can choose any other category).
For independent factors no reference category is needed. Of course you can
code or recode those factors as you please, but SPSS would always analyze
the two or more categories, and their combinations with other factors, to
look for different distributions of responses to your dependent variable.

Hector

> -----Original Message-----
> From: SPSSX(r) Discussion [mailto:SPSSX-L@LISTSERV.UGA.EDU]
> On Behalf Of Marc Scoppettone
> Sent: Wednesday, August 03, 2005 6:44 PM
> To: SPSSX-L@LISTSERV.UGA.EDU
> Subject: Re: Reference Category for Categorical Vars in NOMREG
>
> Hector:
>
> What I mean is this:  suppose on dependent variable takes a
> value of 0 or
> 1 corresponding to "no" and "yes", respectively.  NOMREG sets
> the parameter for 1 equal to 0.  I would prefer to have the
> parameter for 0 set to 0.  I can always invert the odds ratio
> to get the effect of a "yes"
> value, but other softwares (SAS, etc.) give you the option of
> selecting which is set to 0.
>
> Marc
>
> __________ Información de NOD32 1.1185 (20050801) __________
>
> Este mensaje ha sido analizado con  NOD32 Antivirus System
> http://www.nod32.com
>
>