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: RE: FW: GMM and Poisson regression


From   "Lachenbruch, Peter" <[email protected]>
To   "'[email protected]'" <[email protected]>
Subject   st: RE: FW: GMM and Poisson regression
Date   Wed, 19 May 2010 08:15:07 -0700

If your response variable is not a count variable AND contains negative values, the referee is incorrect.  If predictor variables are not counts and/or contain negative values, that's OK.

If you use regression, you can use estat hettest.  With GMM (I haven't used it) it doesn't appear that the hettest is available.

Tony

Peter A. Lachenbruch
Department of Public Health
Oregon State University
Corvallis, OR 97330
Phone: 541-737-3832
FAX: 541-737-4001


-----Original Message-----
From: [email protected] [mailto:[email protected]] On Behalf Of alfredo jimenez palmero
Sent: Wednesday, May 19, 2010 7:17 AM
To: [email protected]
Subject: st: FW: GMM and Poisson regression




Hello all:
 
I just got a review for my paper and I would like to ask for some help here. My paper runs GMM but the review suggests a Poisson regression. Given that my variable is not a count variable and that it does take negative value, how can I do it?
 
I am also asked to provide statistics about the heteroskedasticity, how can I get it in Stata?
 
Finally the model I got some critics because according to the reviewer says that when the time-period is short and the series are persistent, the instruments tend be weak and that the two-step GMM standard errors are downward biased in finite samples. I know that thet problem with the bias is resolved using the Windmeijer correction but what can I do about the first issue?
 
Thank you in advance!
 
Alfredo





¿Sabes que La Gente de Hoy tiene GUARDAESPALDAS contra el Spam? 		 	   		  
_________________________________________________________________
Consejos para seducir ¿Puedes conocer gente nueva a través de Internet? ¡Regístrate ya!
http://contactos.es.msn.com/?mtcmk=015352
*
*   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/

*
*   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