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: Zero Inflated Negative Binomial model
From
Nick Cox <[email protected]>
To
"'[email protected]'" <[email protected]>
Subject
st: RE: Zero Inflated Negative Binomial model
Date
Fri, 20 Jan 2012 13:20:49 +0000
I guess this is evident but recoding to the minimum is problematic if only because that is a biased estimator of the average within each group. So, one possibility is some kind of ordered logit; are there zero-inflated ordered logit models, however?
It's a grim subject but presumably not all self-harmers keep exact records. A more benign analog is number of times a week glancing at Statalist and all I can say in my case is "21-49". That is, as a non-expert I would not trust even the idea of a underlying count variable. That is why the intervals get wider and wider, but the negative binomial model is of course going to take whatever numbers you feed it very literally (which means numerically).
Nick
[email protected]
Eugene Walls
I am working with a dataset that contains counts of the number of times that youth in the sample engage in self-harming behaviors (such as cutting). My co-authors and I are interested in using the zero-inflated negative binomial models because (a) we have a sample that has about 74% zeroes and (b) because we are conceptualizing two processes occurring - one that predicts the likelihood of crossing the threshold into self-injurious behavior and one that predicts the number of times of engaging in the behavior. The Vuong test seems to indicate that the ZINB model is a better fit for the data than the NBReg model.
Our question concerns if it is appropriate to use the ZINB because the response set of the variable capturing the number of times of engaging in SIB is not a straight count, but rather a "0 times" "1 time" "2-3 times" "4-5 times" "6-10 times" "11-20 times" "21-49 times" "50 or more times". We have recoded the variable into 0, 1, 2, 4, 6, 11, 21, 50 using the minimum in the category.but if we do that is using the ZINB model problematic?
*
* 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/