www.cmm.bristol.ac.uk/forum

It is hard to determine what is going on here, especially without seeing the data, however it may be related to around half the data being in one of the categories (NRM Only). Because of this there may be groups where all of the records are in this category. If MQL1 works and PQL2 doesn't then I would suggest looking at the level-2 residuals for the MQL1 model as the residuals are used for the PQL2 estimation.

We often suggest running these type of model using MCMC, have you tried this and if so do the results look sensible?

Thanks Charlton, I formed a binary of the variable and it worked. Thanks for your assistance