I am using non-nested data for a multi-level analysis and was wondering, if it is possible to calculate other model-fit parameters than the -2LL, which MLwiN automatically does. In the literature I have found, that the BIC (Bayesion Information Criterion) would be most useful for me. Is it possible to get it with MLwin?
Thank you very much for your support!
Best wishes,
sinavera
BIC with MLwin?
Re: BIC with MLwin?
Hi Sinavera,
MLwiN only calculates the deviance (-2LL) though generally BIC is a simple formula involving this quantity and the number of parameters in the model and number of observations in the dataset. Things are not quite as simple in multilevel models as there is some disagreement onto what one uses for number of observations due to the correlation induced by the multilevel structure. We therefore don't supply the BIC but do not preclude others from calculating it themselves.
Hope this helps,
Bill.
MLwiN only calculates the deviance (-2LL) though generally BIC is a simple formula involving this quantity and the number of parameters in the model and number of observations in the dataset. Things are not quite as simple in multilevel models as there is some disagreement onto what one uses for number of observations due to the correlation induced by the multilevel structure. We therefore don't supply the BIC but do not preclude others from calculating it themselves.
Hope this helps,
Bill.