Multilevel Zero inflated negative bionomial (ZINB) model

[Jie Gao]

Dear Statalist members,

I am working on my paper with constructing a three-level regression analysis. However, my travel survey dataset with an excess of zeros, as a consequence of relatively large share of respondent's not performing trips by a certain travel mode. I think I may need to use Multilevel Zero-inflated negative binomial model. How to implement this kind of multilevel model? Could you please give me an example code, since I am a Stata beginning learner. Thanks in advance.

Best,
Jie

[Phil Bromiley]

You didn't get a quick answer. You'll increase your chances of a useful answer by following the FAQ on asking questions - provide Stata code in code delimiters, readable Stata output, and sample data using dataex.

You don't provide sufficient information to really understand your problem. Why do you need a multilevel model? What are the levels? Are they of specific interest or just as controls?

Before asking any question, you should Google the issue. Searching for "multilevel zero-inflated negative binomial regression stata" gives some insightful discussion. Have you looked at:
https://www.stata.com/statalist/arch.../msg00784.html
https://www.stata.com/statalist/arch.../msg01407.html
https://www.stata.com/statalist/arch.../msg01106.html
https://www.statalist.org/forums/for...nflated-models

You might have better luck with a zero inflated Poisson model.

[Bill Schreckhise]

Jie Gao,
Did you ever figure out how to do a multilevel ZINB model in Stata? If you did, would you mind sharing that information with me? I'm trying to do the exact same thing. Thanks!