I am running a multiple group multinomial logistic regression. I am using the knownclass option to indicate group membership, as multiple group analysis is not available for type=mixture. I have 3 groups of countries, meaning that I know observations within countries are not independent from one another. Thus, I want to correct for this using clustered standard errors. I have read to use type=complex in combination with the cluster= command. However, I get the following error message:
*** WARNING in VARIABLE command CLASSES option is only available with TYPE=MIXTURE. CLASSES option will be ignored. *** WARNING in VARIABLE command KNOWNCLASS option is only available with TYPE=MIXTURE.
How should I proceed? Is it possible to combine multiple group analysis, multinomial logistic regression and the clustering of standard errors?