www.cmm.bristol.ac.uk/forum

Hi Sabine, The estimates from MQL / PQL are quasi-likelihood so you cannot do a standard likelihood-based test to get a P value. You can do an approximate Wald test via the intervals and tests window but bear in mind this assumes normality for the variables so is only an approximation. Hope that hel...

If you leave it unconstrained then it is simply pointing to the maximum (quasi)likelihood solution being 0 for the variance i.e. there is probably no influence of the hierarchical structure. You could try fitting the model using MCMC to see what estimates that gives,
Bill.

Dear KW844529, What you are doing doesn't make sense at all as in the logistic regression model, value normally used for the level 1 variance stored in that column is in fact the scaling factor for over/underdispersion and set at 1 for a standard logistic regression with binomial variation. It there...

The effective sample size and Raftery Lewis are completely different diagnostics and in fact a low Raftery Lewis number is good as the diagnostic is a minimum number to run for. In contrast a high ESS is good as it gives an estimate of the equivalent number of independent estimates for the parameter...

Dear GKonyarov, Thanks for the post. I have read it a couple of times and although you describe your models I wasn't sure what exactly question you are asking here? Apologies that in lockdown I have been a bit slow to look at the forums and sadly we have lost our colleague Harvey Goldstein whose pap...

Hi Ashley, Thanks for your question. I am a bit rusty on these sorts of models and taking a quick look at the equations window in MLwiN when you try and fit multivariate response models you are restricted to responses being normal, binomial or Poisson. I don't know if this has changed since the slid...

Hi Ken, Apologies that this one hasn't been answered after so long. Basically I think R2MLwiN has a very similar syntax to glmer and thus will likely fit the same models. They are using different algorithms so I am not sure which will be the quicker. I suspect estimates for 2 models would be similar...

Hi Sun,
Not really as as you say you don't have normality so any use of the SEs would be very approximate. you might consider bootstrapping I guess but easiest with MCMC.
Best wishes,
Bill.

Hi Sun, With regard MCMC my suggestion is to look at my MCMC manual where I cover how one works out confidence intervals for derived quantities - here I cover in section 4.7 the difference between 2 schools, 4.8 their ranks with CIs and most relevant for you the ICC/VPC in section 4.9. Here you can ...

Hi Rachael,
MCMC is fitting a Bayesian model so the concept of a classical P value is not valid for MCMC estimates - I think we do offer Bayesian P values for all parameters though which basically check what proportion of iterations are positive / negative for a chain.
Best wishes,
Bill.