www.cmm.bristol.ac.uk/forum

Hi Rdmcdowell, Thanks for the clarification. Good to see people using my MCMC book :) The first thing to note is that a variance of 4.5 is crazily big in a logistic regression model (particularly if you are getting this from the default 1st MQL) and would usually indicate that most clusters are all ...

Hi Rdmcdowell, When you say do not work well do you mean simply that the chains mix poorly? My only experience here really is in my paper Browne et al. (2007) in Statistical Modelling - https://scholar.google.com/citations?view_op=view_citation&hl=en&user=mxNZAmoAAAAJ&cstart=20&pages...

No worries both. Basically if the probability of being in categories k and upwards is p then the probability of being in categories k-1 and downwards will be 1-p and if logit(p) = a then logit(1-p) = -a hence when you switch the base category then the main change will be a switching of signs for all...

Hi rdmcdowell,
Am afraid I didn't write runmlwin so can't help here though I'll mention this to George Leckie and Chris Charlton to reply to you,
Best wishes,
Bill.

Hi Vivian, I suspect this is pretty challenging for a cross-classified scenario. Lemma module 7 has a section on PA for 2-level binomial and the simulation approach (section 7.4) and my guess is that to do cross-classified equivalent calculations would require an additional level of looping in the s...

Hi ddswick,
To confirm the Hosmer-Lemeshew test has not been implemented in MLwiN. In the multilevel setting there are residuals available and the diagnostics that go with testing these are available as in normal models.
Hope that answers your question.
Best wishes,
Bill.

Hi Vivian, Thanks for your question. I wonder whether you can clarify a bit? When you talk about reversing the sign of the coefficient is this because of the base category you have chosen in the cumulative logit? I.e. if you are using the lowest category as base then the values for the thresholds wo...

Hi RDMCDOWELL, If you fit a cross-classified model then it's best to use MCMC in MLwiN and so you would have higher levels/classifications for doctors and patients. I wouldn't suggest you use the clustering as described. I think the IGLS method would really struggle. The multiple membership approach...

Dear Gerine, I will agree with Kelvyn that this is indeed a challenging problem due to the scaling that occurs. I don't know Tony Fielding's paper that well so don't think this has been implemented in MLwiN unless he wrote macros himself. With regard VPC estimation there are 2 references (Goldstein,...

Hi Gerine, A better approach would be to extract the chains for the 2 dummies and subtract their values as this would then give you a chain for the differences. You could then look to see if the quantiles of this chain contain 0. This is better as it will deal with any correlation between the parame...