Dear Mplus team, I'm running a MGA to establish invariance of a ML model of 177 individuals nested in 34 teams, and the two groups are US and Europe - the model doesn't run, and I get the below message: THE MODEL ESTIMATION DID NOT TERMINATE NORMALLY DUE TO AN ILL-CONDITIONED FISHER INFORMATION MATRIX. CHANGE YOUR MODEL AND/OR STARTING VALUES. I have already tried setting the very low between-level variances@0, but no success. The error message continues telling me: THE STANDARD ERRORS OF THE MODEL PARAMETER ESTIMATES COULD NOT BE COMPUTED. Any advice would be much appreciated.
Thank you Prof Muthen. This particular model runs for the European group separately (24 teams, 129 individuals), but NOT for the US group separately (10 teams, 48 individuals). (With a modified models using item parceling, it is the other way around)
I don't know how many parameters your model has, but 48 individuals in 10 clusters is quite small. It is recommended to have a minimum of 30 clusters. Note also that if the same model does not fit well in each group, comparisons across groups are not valid.