[R-sig-ME] how to specify the response (dependent) variable in a logistic regression model

[John Kingston]

Dear colleagues,
I hope this is the right forum for asking this question.

I have data from an experiment in which participants were asked to give one
of four responses to stimuli. The responses could be characterized as
representing the possible value of two variables, such that:

Response Variable 1 Variable 2
1               0               0
2               1               0
3               0               1
4               1               1

The possible responses are therefore neither ordinal nor multinomial in
character.

I have run three separate logistic regressions in which the responses 2, 3,
and 4 were each compared to response 1. The results are all sensible and
interpretable in terms of the expected effects of the three independent
variables. But I'm worried that doing so has required taking subsets from
responses that were collected together, and that the model interpretation
is thereby compromised.

I can provide more information about the model specification if that would
be helpful

Any advice or a referral to the right forum would be greatly appreciated.
Best,
John

John Kingston
Professor
Linguistics Department
University of Massachusetts
N434 Integrative Learning Center
650 N. Pleasant Street
Amherst, MA 01003
1-413-545-6833, fax -2792
jkingstn using umass.edu
https://blogs.umass.edu/jkingstn
<https://blogs.umass.edu/jkingstn/wp-admin/>

	[[alternative HTML version deleted]]