Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | "Nick Cox" <n.j.cox@durham.ac.uk> |
To | <statalist@hsphsun2.harvard.edu> |
Subject | RE: st: Poisson regression -not concave- |
Date | Mon, 7 Jun 2010 10:02:32 +0100 |
There's also a flavour of circular argument if the response is y and one of the predictors is (y > 0). Nick n.j.cox@durham.ac.uk Maarten buis --- On Mon, 7/6/10, Paolina Medina wrote: > I'm trying to run a poisson regression model in which the > dependent variable is the number of mobile phones from the > households, and among other explanatory variables i am > using a dummy wariables which takes the value of 1 when > the household has at least one cell phone and zero > otherwise. Sounds to me you want to do something like a -zip- rather than a -poisson-, i.e. you want to handle the zero counts differently from the other counts. * * 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/