Statalist


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

Re: st: Inverse Mills Ratio After Negative Binomial Regression Model


From   Maarten buis <maartenbuis@yahoo.co.uk>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Inverse Mills Ratio After Negative Binomial Regression Model
Date   Tue, 16 Sep 2008 07:31:23 +0100 (BST)

--- Rodwan M Abouharb <roda@lsu.edu> wrote:
> I have two equations which I would like to link. The first equation
> is an event count, the second is an ordered logit. How can I generate
> an inverse mills ratio after using a negative binomial regression
> model? I have seen inverse mills ratios for logit and ordered logit
> models but not one for a NBREG.

I believe that the inverse Mill's ratio is based on
normality/Gaussianity of the error term in the regression equation of
the (latent) dependent variable against the explanatory variables. So
it applies to selection in a linear regression and in probit and
ordered probit, but not in logit or ordered logit or negative binomial
regression. But I could be wrong.

-- Maarten

-----------------------------------------
Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands

visiting address:
Buitenveldertselaan 3 (Metropolitan), room N515

+31 20 5986715

http://home.fsw.vu.nl/m.buis/
-----------------------------------------


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