[R] is there anything wrong with doing a multinomial logistic like it is a binary logistic regression?

[Michael Dewey]

At 04:13 17/08/2013, Eunice Chou wrote:
>My outcome variable (y) is 3 categories. Is there anything bad about using
>the following code to get a parameter estimate for my bivariate model?
>
>publicfit = glm(y ~ public, data=dataSPSS.vmj, family=binomial)

Have you tried it? What did R tell you?


>         [[alternative HTML version deleted]]

Michael Dewey
info at aghmed.fsnet.co.uk
http://www.aghmed.fsnet.co.uk/home.html