Thank you very much for the answers so far.

I like the idea of ordered probit but am a bit worried that it assumes
the linear ordering that I want to demonstrate. (Proposition 13 was
definitely more extreme than proposition 8 but the question is, are
voters voting sophisticatedly or sincerely, or just confusedly).

On the other hand, could I detect any association between moderation
and voting on 8 in a multinomial logit? Because my IVs are categorical
(or ordinal), and the hypothesized relationship is nonlinear, I am not
sure what to expect from the coefficients.

Cheers
David

**********************************************************
             Political Methodology E-Mail List
        Editor: Karen Long Jusko <[log in to unmask]>
**********************************************************
        Send messages to [log in to unmask]
  To join the list, cancel your subscription, or modify
           your subscription settings visit:

          http://polmeth.wustl.edu/polmeth.php

**********************************************************