Dear all,

I had posted this a while ago and not received a response. Am reposting in case someone has some advice for me!

I have a simple question. I am using cmclogit for a model of firm relocation destination county choice, with the main explanatory variables being county-specific variables. Would cmmixlogit be a more appropriate for these kind of data?

Also, Is it inappropriate for some cases to have a different number of alternatives? In other words, can I exclude some alternatives (counties) for some cases because those counties were not in existence in particular years?

Thanks in advance,
Chirag