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: Interpreting zero-inflated negative binomial Stata output (zinb / zip)
From
Tanuku AP <[email protected]>
To
Stata <[email protected]>
Subject
st: Interpreting zero-inflated negative binomial Stata output (zinb / zip)
Date
Sat, 20 Aug 2011 19:01:25 -0400
Hello all,
The reference entries for zero-inflated poisson and negative binomial are quite scant (at least to me). I didn't find much either in the list archive or Stata Journal archives.
There is an example on: http://www.ats.ucla.edu/stat/stata/output/Stata_zinb.htm. ; The UCLA example explanation seems to match the inflate() option description in the manual i.e. the logit model determines certain zero outcome. This seems different from the norm for --logit--, where non-zero value is defined as success. Is the UCLA explanation correct?
May I also ask if people could refer me to zinb examples that have more interpretive explanations for the estimates [I didn't find much in Baum's Intro book as well as Cameron & Trivedi's book]. While Cameron & Trivedi discuss zip / zinb, they don't go into the details of interpreting the coefficients.
Also, the irr option seems to exponent the second stage estimates and not the first-stage logit estimates. I wish Stata manual had more details / examples.
--
Thanks,
Tanuku
*
* 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/