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: zinb for Zero-inflated negative binomial regression


From   "Jacobs, David" <jacobs.184@sociology.osu.edu>
To   "'statalist@hsphsun2.harvard.edu'" <statalist@hsphsun2.harvard.edu>
Subject   st: RE: zinb for Zero-inflated negative binomial regression
Date   Thu, 3 Oct 2013 21:56:41 +0000

One possibility that's worth trying concerns your offset term.  If it is something like population--which tends to be a large number in comparison to the numeric size of your other explanatory variables--you might solve your problem by dividing by a constant like 100,000 or some such to bring the numeric size of your offset variable closer to the same general size as that of your other variables.  

More generally, the count estimators and particularly the zero-inflated versions often have difficulty converging, but the above trick has worked for me.

Hope this simple remedy helps.

Dave Jacobs

-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Caroline Wilson
Sent: Thursday, October 03, 2013 3:05 PM
To: statalist@hsphsun2.harvard.edu
Subject: st: zinb for Zero-inflated negative binomial regression

Hi everyone,

I'm new to using the zinb command in Stata (for a Zero-inflated negative binomial regression) and had a few questions about my code:

This is my current code:

zinb test var_m var_l var_c, inflate(var_m var_l var_c, offset(var_l)) vce(cluster group1)


1. I'm trying to add an offset variable to the model (var_l).  I have added it by including ", offset(var_l)" in the code. However, when I run the model including the offset terms it just runs indefinitely (while it runs fine when I don't include this). Is there something wrong with how I have specified this? 

2. I'd like to look at residuals for some of the linear terms in the model. How might I do this with zinb?

3. I'd like to account for clustering of people within group1. Is adding "vce(cluster group1)" the correct way to handle this?

Many thanks!
Caroline 		 	   		  
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/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/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


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