Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Nick Cox <njcoxstata@gmail.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | Re: st: which -cmp- option to use for poisson model with count data? |
Date | Thu, 3 May 2012 13:40:47 +0100 |
We've got to nail this one. Laura's not said so, but what I wildly imagine is this: Somehow Laura is counting how many experts do or say something. There is a fixed number of experts being recorded, so in principle any number from 0 to all of them could be observed. That's the outcome or response variable. If that is so, I don't think this is very Poisson-like. It's not like number of children, where there is no known upper limit. You may have 17 children, but it could be 18 or 19 or whatever. If the upper limit is known and definitely bites some of the time, that's not Poisson-like. The upper limit can vary too; that's fine. Please Laura: You should give substantive detail here to describe the process. Describe how the data are produced. Otherwise, this is just going round in circles (or more likely commenters will give up in despair). Nick On Thu, May 3, 2012 at 1:12 PM, Brendan Halpin <brendan.halpin@ul.ie> wrote: > On Thu, May 03 2012, Laura R. wrote: > >> dependent variable: >> - experts >> - in this sample: 0 to 5 >> - 0 should be in the analysis (not "missing") >> - in other samples, it can be more than 5, but naturally not less than 0 > > This makes it sound as if the DV isn't bounded at 5, but simply that > there are no higher values observed in this sample. If that's true, > models for counts (poisson etc) should be fine. > > Brendan > -- > Brendan Halpin, Department of Sociology, University of Limerick, Ireland > Tel: w +353-61-213147 f +353-61-202569 h +353-61-338562; Room F1-009 x 3147 > mailto:brendan.halpin@ul.ie ULSociology on Facebook: http://on.fb.me/fjIK9t > http://teaching.sociology.ul.ie/bhalpin/wordpress twitter:@ULSociology > * > * For searches and help try: > * http://www.stata.com/help.cgi?search > * http://www.stata.com/support/statalist/faq > * http://www.ats.ucla.edu/stat/stata/ * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/