www.cmm.bristol.ac.uk/forum

Hi Chris,

Thanks for this. I have checked the trajectories for the MCMC estimations and they look fine.

I just need to double-check that it is correct to use MCMC estimation, even for single-level models?

Hi,

I am doing some binomial logistic regression modelling. In the past I have always estimated my models using both IGLS and MCMC, but this was because my models were cross-classified and as such required MCMC estimation.

I am now running binomial logistic regression models, but they are either ...

Hi Chris,

Thanks for that. I tried it as a linear model instead of a logistic model and that resolved the problem, but I may try your idea as well - see if I can get the logistic to go.

Thanks again,

Caroline.

Hi,

I'm currently running a model in mLwiN with 128 school fixed effects and am getting this error message:

V gone -ve definition for block 0 iteration aborted (random pass)(moni)

Does anyone know how to resolve this?

Thanks in advance.

Brilliant. Thanks, Chris, that's done it - cheers.

I have just read some new data into MLwiN (from SPSS), which is fine, but when I specify the equation for the model, I get this error message:

"wrong parameters - possible name clash between column and macro(post)"

Unfortunately, this isn't an error message I'm familiar with.

Does anyone know ...

I have now copied the entire dataset into a new MLwiN worksheet and it seems to be working.

The reduction in the DIC should be at least 10 otherwise the two models are not substantially different, i.e. the parameter you are adding is not significant. So, if by adding your level-2 variable you see a reduction of less than 1, it is not worth including in the model.

Hi,

I have successfully run a number of models using a continuous outcome variable, with varying degrees of complexity - up to 5 levels and over 30 fixed effects (in MLwiN 2.26). However, now I am using the same dataset to run a binomial, logistic model, I am able to specify the equation, but when ...

Great stuff. Thanks, Chris.