Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: -qvf- : endogeneity and negative binomial model


From   Justina Fischer <justina.fischer@unisg.ch>
To   statalist@hsphsun2.harvard.edu
Subject   st: -qvf- : endogeneity and negative binomial model
Date   Sun, 21 Oct 2007 21:23:12 +0200

Hi

in a previous threat (e.g. http://www.stata.com/statalist/archive/2005-01/msg00464.html by Vince Wiggins)  the applicability of -qvf- to an endogenous variable in a probit model was discussed. The conclusion was that it should not be applied to cases of reverse causality, but well to cases of measurement errors.

Is this also the cause for a negative binomial model, in which I case I would then resort to ivtobit and ivreg2 ?

Thanks

Justina



Dr. Justina A.V. Fischer, M.A.
University of St. Gallen
CH-9000 St. Gallen




© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index