Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Jibonayan Raychaudhuri <jibonayanrc@yahoo.com> |
To | "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu> |
Subject | st: Multilevel Poisson with constraints |
Date | Tue, 16 Aug 2011 00:31:36 -0700 (PDT) |
Hi Statalist Users, I am estimating a Multilevel poisson model in Stata. Basically, I am modelling the number of visits to different recreational sites as a function of a host of explanatory variables. I have two queries regarding my model: (1) There is a theoretical justification for modelling the dependent variable as a logarithmic function of one of the independent variables. The model that I estimated is as follows: xtpoisson nvisits x1 x2 x3 log(x4) x5, i(site) normal However given that this is Poisson model, I am not sure how to interpret the coefficient of x4. (2) I would like to impose an inequality constraint on the estimated coefficients of x1 and x2 viz., _b[x1]+_b[x2]>=0 Will that be possible to do in xtpoisson? If yes, how? Any help will be much appreciated. Best, Jibonayan * * 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/