Re: [R] Analysing ordinal/nominal data

From: Piotr Majdak <piotr_at_majdak.com>
Date: Sat 18 Jun 2005 - 01:28:55 EST

Hi Brian (and the list of course!),

I still have problems analysing data in R, because I don't know how to tell glm() "use row-effect model, please". The models are well defined by Agresti, but can't get the link from the theory to the implementations in R. Different names, definitions and no explanation of results in the documentation of glm() or summary() make it hard to get in...

But I found another solution for my data: I just use the saturated log-linear model for categorial data and refer to the estimated parameter of the three-way-interaction only. That's enough statistics for my paper ;-).

Thanks for your help,

Piotr Majdak

Prof Brian Ripley wrote:

> As I suggested before, a binomial logistic model is appropriate here,
> not a Poisson log-linear one. (They are equivalent, but the binomial
> version is easier to interpret and less wasteful to fit.)
>
> You have still not defined v' and w', nor the scores (are they estimated
> or not). But the model I suggested is such a model with scores 1,2,...

-- 
Piotr Majdak
Acoustics Research Institute
Austrian Academy of Sciences
Reichsratsstr. 17
A-1010 Vienna
AUSTRIA
phone: +43-1-4277-29511
fax: +43-1-4277-9296
email: piotr@majdak.com
WWW: http://www.kfs.oeaw.ac.at

______________________________________________
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Received on Sat Jun 18 01:54:37 2005

This archive was generated by hypermail 2.1.8 : Fri 03 Mar 2006 - 03:32:48 EST