Interpret var (bcons.1) & var (bcons2.1)

Welcome to the forum for MLwiN users. Feel free to post your question about MLwiN software here. The Centre for Multilevel Modelling take no responsibility for the accuracy of these posts, we are unable to monitor them closely. Do go ahead and post your question and thank you in advance if you find the time to post any answers!

Remember to check out our extensive software FAQs which may answer your question: http://www.bristol.ac.uk/cmm/software/s ... port-faqs/
Post Reply
Zhen2018
Posts: 2
Joined: Wed Oct 31, 2018 12:45 pm

Interpret var (bcons.1) & var (bcons2.1)

Post by Zhen2018 » Sat Feb 16, 2019 10:23 pm

Hi, I fitted a negative binomial model in MLwiN , and wondered if anyone could help me interpret the random part of the output please. It shows var (bcons.1) =1.00 (SE: 0.00) , var (bcons2.1) = - 0.04 (SE: 0.00). I would be very grateful if you could advise me how to interpret var (bcons.1) and var (vcons2.1). Thanks!

ChrisCharlton
Posts: 1103
Joined: Mon Oct 19, 2009 10:34 am

Re: Interpret var (bcons.1) & var (bcons2.1)

Post by ChrisCharlton » Tue Feb 19, 2019 4:25 pm

I passed this question on to Professor Kelvyn Jones and he gave the following answer:
The lowest level random part of NBD does not really admit to much interpretation; it really allows for more overdispersion than a Poisson, and when it is over dispersed the standard errors of the fixed part take account of this overdispersion and the partitioning of the variance with higher levels can change.

In a Poisson model the level 1 variance if fitted as a linear function of the mean (derived from the fixed part), so that the estimated parameter will be constrained to 1; that is the level -1 variance will be equal to the means (that is what bcons.1 is doing in MLwiN); the variance is not a freely estimated parameter.

In the NBD model, the level -1 variance is a quadratic function of the mean; there is the linear bit which is constrained (associated with bcons1) and the quadratic bit (associated with bcons2.1) that is now estimated. Somewhat surprisingly here this is a negative value (indicating underdispersion) but is numerically not very large. (-0.04). I suggest you fit a strict Poisson (in effect constrain the quadratic term to 0.00) and see if it makes a big difference to the parameters of real interest. You can get underdispersion when analyses a correlated repeated measures data but I have not seen much on it.

Zhen2018
Posts: 2
Joined: Wed Oct 31, 2018 12:45 pm

Re: Interpret var (bcons.1) & var (bcons2.1)

Post by Zhen2018 » Wed Feb 20, 2019 10:25 pm

Many thanks to you and Professor Kelvyn Jones for answering my questions. That's very helpful!

Post Reply