Page 1 of 1

Zero-inflated negative binomial models?

Posted: Tue Aug 08, 2017 2:31 pm
by adeldaoud
Hello,

Can Mlwin fit zero-inflated negative binomial models? I know that we can fit Poisson and negative binomial models.

thanks in advance
Adel

Re: Zero-inflated negative binomial models?

Posted: Wed Aug 09, 2017 3:14 pm
by ChrisCharlton
Unfortunately MLwiN cannot fit these models. Professor Kelvyn Jones suggests however that you may wish to read the article at https://statisticalhorizons.com/zero-inflated-models as it may be that you may not need to use a zero inflated model.

Re: Zero-inflated negative binomial models?

Posted: Thu Aug 10, 2017 1:10 pm
by adeldaoud
Thanks for the link, Chris. Interesting article. As the article states, we have theoretical reasons to test the statistical efficiency of a multilevel zero-inflated negative binomial model and a regular multilevel negative binomial model. I assume you or Kelvyn are not aware of any (R) package that can estimate these types of multilevel models?

By the way, does the online learning facility (LEMMA) has teaching material on negative binomial models? I cannot locate it. (Interested specifically in the R2mlwin learning experience of negative binomial models, but general learning material is fine too )

Thanks in advance

Re: Zero-inflated negative binomial models?

Posted: Fri Aug 11, 2017 8:21 am
by ChrisCharlton
I am not familiar with any R packages that handle these models.

There are currently no LEMMA modules that cover these model types, however Kelvyn is in the process of writing a module on count data which should fill this gap.

Re: Zero-inflated negative binomial models?

Posted: Fri Aug 11, 2017 8:36 am
by adeldaoud
Ok, thanks, Chris.

Looking forward to reading Kelvyn's module.

Re: Zero-inflated negative binomial models?

Posted: Sat Apr 21, 2018 3:00 am
by yongjookim78
This looks very helpful and thanks for the useful discussion everyone!