www.cmm.bristol.ac.uk/forum

Hi Marjolin,
Don't see any problem here - your variables appears to explain 2 thirds of the level 3 variation and the Z score is only 4.3 which although very significant you do have 6000 data points and so it is possible to have much bigger Z scores.
Best wishes,
Bill.

Hi Zuzanna, The DIC is an information criterion like the AIC and BIC in classical statistics and basically such quantities do not have an underlying statistical distribution and so the concept of significance doesn't work for such measures. It is therefore just the case that rules of thumb are used ...

Hi Griet,
In theory a nested structure is a special case of the more general crossed-structure with no crossing !! So yes there is no restriction here and if you tried selecting cross-classified for a nested structure you should get the same answers.
Bill.

Hi Griet, It shouldn't matter but (1) you should make sure you tick the cross-classified button so that it is fitting the XC model! (2) you should ensure you run the MCMC estimation for sufficiently long that the chains converge to similar answers - they will not be exactly the same due to the Monte...

Hi Ine, What you are proposing would be a false replication i.e. you will be pretending you have more data than you have (particularly if you didn't put in the level 2 random effect). In fact once you put the random effect in unsurprisingly it will show all the variance is at level 2 and might in so...

Hi Nina,
Not sure I understand your question with regard the per group statement. The model will have a variance at level 1 and level 2 and residuals at level 2 but there isn't a different variance for each group in this model.
Best wishes,
Bill.

Hi Marie,
To compare models 2 and 3 you can fit them both using runmlwin and MCMC and then compare the 2 DIC values.
Regards,
Bill.

Hi Moletsane Monyake, It is perfectly acceptable to collapse ordered categories into smaller numbers of categories on practical grounds and as you say on ease of interpretation grounds. I wouldn't worry too much about things like residuals etc. which are often hard to interpret for ordered category ...

Hi Stuart, Some thoughts. As you are looking at change and you only have 2 time points then I would have thought you would be considering the baseline as a predictor variable and the second time point as the response thus removing your time point level. As for your behaviours I would suggest that he...

Hi jellie1410,
I guess your best bet is to look for examples where multilevel models have been used in the journal in question and copy the conventions used. Some journals simply have tables with coefficients, some with binary responses use odds ratios etc.