Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: Test between NB1 and NB2 in Stata 10.1


From   "Petra Nieken" <petra.nieken@uni-bonn.de>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: Test between NB1 and NB2 in Stata 10.1
Date   Thu, 19 Jan 2012 10:42:25 +0100

Dear Stata List Users,

I use Stata/SE 10.1 and I am estimating a negative binomial regression. I am
now looking for a way to test if I should use a NB1 specification
(dispersion constant) or a NB2 specification (dispersion mean). In the
literature I found that I could use a Vuong test but I only found the Vuong
test for zero-inflated or zero-truncated negbin models. To calculate it by
hand I need the predicted probabilities. However, ?predict test,
pr(dependent_variable)? does not work in Stata 10.1. This option is not
allowed after nbreg.
Does anyone know how to solve this problem?

Thanks for your consideration.

Kind regards,

Petra Nieken


Dr. Petra Nieken
Universität Bonn
Institut für Gesellschafts- und Wirtschaftswissenschaften
Betriebswirtschaftliche Abteilung II
Lehrstuhl für Personal- und Organisationsökonomie
Adenauerallee 24-42
53113 Bonn
Tel: 0228-739213
Fax: 0228-739210



*
*   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/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index