Dear all,

I would like to run a multinomial logistic regression for (unbalanced) panel data in Stata 14.2. In other posts, the commands -femlogit- and -mlogit- with cluster(panelid) have been suggested for such a calculation. Is it fair to say that -femlogit- is the better approach, since it was developed for panel data?

I am curious to hear your answer. Thanks in advance.