RE: [R] Analysis of ordinal categorical data

About this list Date view Thread view Subject view Author view Attachment view

From: John Fox (jfox@mcmaster.ca)
Date: Thu 06 May 2004 - 00:48:06 EST


Message-id: <20040505144805.TGHW11251.tomts36-srv.bellnexxia.net@JohnDesktop8300>

Dear Thomas,

Barring a numerical problem, polr() will fit the model as a mechanical
matter, but the proportional-odds model and other, relatively parsimonious,
models for ordinal data, make assumptions about the structure of the data. I
don't think that it's sensible to explain the model in detail here; you
could consult a text that discusses the model -- it's a standard topic in
categorical-data analysis. Two sources are Venables and Ripley's Modern
Applied Statistics with S (with which the MASS package is associated) and my
own R and S-PLUS Companion to Applied Regression.

Regards,
 John

> -----Original Message-----
> From: r-help-bounces@stat.math.ethz.ch
> [mailto:r-help-bounces@stat.math.ethz.ch] On Behalf Of
> thsudler@swissonline.ch
> Sent: Wednesday, May 05, 2004 9:29 AM
> To: r-help@stat.math.ethz.ch
> Subject: [R] Analysis of ordinal categorical data
>
> Thanks a lot for your advice. What do you mean with "the
> proportional-odds assumption may not hold"? Does this
> solution with "polr" always works? Or what's important to
> take into account?
>
> Regards
> Thomas
>
> >Dear Thomas,
> >
> >One approach to an ordinal response variable is the
> proportional-odds
> >model, implemented in the MASS package as polr(). The
> proportional-odds
> >>assumption may not hold, however.
> >
> >I hope this helps,
> > John
> >
> > -----Original Message-----
> > From: r-help-bounces@stat.math.ethz.ch
> > [mailto:r-help-bounces@stat.math.ethz.ch] On Behalf Of
> > thsudler@swissonline.ch
> > Sent: Wednesday, May 05, 2004 7:45 AM
> > To: r-help@stat.math.ethz.ch
> > Subject: [R] Analysis of ordinal categorical data
> >
> > Hi
> >
> > I would like to analyse an ordinal categorical variable. I
> know how I
> > can analyse a nominal categorical variable (with multinom
> or if there
> > are only two levels with glm).
> >
> > Does somebody know which command I need in R to analyse an ordinal
> > categorical variable?
> >
> > I want to describe the variable y with the variables
> x1,x2,x3 and x4.
> > So my model looks like: y ~ x1+x2+x3+x4.
> >
> > y: ordinal factor variable with levels (never, rare,
> bychance, often).
> >
> > Thanks a lot in advance
> > Thomas
> >
> > ______________________________________________
> > R-help@stat.math.ethz.ch mailing list
> > https://www.stat.math.ethz.ch/mailman/listinfo/r-help
> > PLEASE do read the posting guide!
> > http://www.R-project.org/posting-guide.html
>
> ______________________________________________
> R-help@stat.math.ethz.ch mailing list
> https://www.stat.math.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide!
> http://www.R-project.org/posting-guide.html

______________________________________________
R-help@stat.math.ethz.ch mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html


About this list Date view Thread view Subject view Author view Attachment view

This archive was generated by hypermail 2.1.3 : Mon 31 May 2004 - 23:05:07 EST