Re: Statistical evaluation of categorical data

["Ward R. Drennan" <drennan@xxxxxxxxxxxxxxxx>]

We used a multinomal logistic regression: Drennan et al. 2003, JASA 114 (4),
2178-2189.

Key references were:

Agresti, A.1990. Categorical Data Analysis Wiley, New York (see pp.
313-317).
and
Long, J. S. 1997. ''Nominal outcomes: Multinomial logit and related models,''
in Regression Models for Categorical and Limited Dependent Variables
Sage, Thousand Oaks, CA pp. 148-178.

The analysis was done in SAS. It was pretty complicated. We consulted with a
statistics guru.
Viel Glueck, Ward

----- Original Message -----
From: "Piotr Majdak" <piotr.majdak@xxxxxxxxxx>
To: <AUDITORY@xxxxxxxxxxxxxxx>
Sent: Tuesday, May 03, 2005 7:22 AM
Subject: Statistical evaluation of categorical data


> Dear list,
>
> I've got some categorical data (Yes/No responses) from ONE subject as
> responses to acoustical stimuli under different conditions. Each
> condition was repeated 60 times, shuffled with all conditions in one
> experiment - just the method of constant stimuli. Four independent
> variables control the conditions, 2-3 categories each one (some of them
> are ordinal). Now I'd like to analyse the main effects and interactions
> of all variables on the responses.
>
> Do you know how to treat the data and which evaluation method am I
> supposed to use? Can you point me to some references about evaluation of
> this kind of data?
>
> Thanks in advance,
>
> Piotr Majdak
>
>
> --
> Please avoid sending me Word or PowerPoint attachments.
> See http://www.fsf.org/philosophy/no-word-attachments.html
>
> 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@xxxxxxxxxx
> WWW: http://www.kfs.oeaw.ac.at