Dear Political Methodology List Members,

I have a question about count models.  My dependent variable is a count for
each U.S. state.  I'd like to divide that count by the state's population so
that I have a per capita count.

Can I still use the resulting dependent variable in a count model
(specifically, a fixed effects negative binomial model)?  The data were
still generated by a count process, but the values are no longer integers.

I've been advised that this is much like the case when one has counts based
on different lengths of exposure.  Can anyone point me to research that's
analyzed similar data?

Thanks in advance,
Brendan

--
Brendan J. Doherty
Doctoral Candidate
Travers Department of Political Science
University of California, Berkeley

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

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