Back in early May, Mark Boye <[email protected]> asked:
>> Following Hardin & Hilbe, I have estimated a negative binomial with glm
>> -fam(nb, #) - in order to use GLM diagnostics. Thereafer, again following
>> H&H, I attempted residual analysis with the use of Anscombe residuals.
>> Unfortunately, however, the predict command returns only missing values.
>> Why is this so? Am I missing something?
and I responded:
> Mark seems to have uncovered an error in the calculation of Anscombe
> residuals after -glm- used with the negative binomial family. We are
> currently working to confirm that this is indeed a bug (and our initial
> indications are that it most likely is), and on the fix.
> I'll report back to the list when I have something more definite to say on
> this matter.
This was a bug. An incorrect formula was being used in the calculation of
Anscombe residuals (-predict, anscombe-) after -glm- with either a negative
binomial or a non-Bernoulli binomial family.
We have fixed this, and you can gain access to the fix by making your Stata
executable/ados up-to-date.
--Bobby
[email protected]
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
