Re: [R] Latent class multinomial (or conditional) logit using R?

Hi Christian, Thanks a lot for the suggestion. As you expected, lcmixed does not provide more functionality than poLCA for the case of only categorical data... Do you know whether there is an explanation (some technical difficulty I may be missing, I am Economist so it is very likely) of why I can

[R] Latent class multinomial (or conditional) logit using R?

Hi everyone? Does anybody know how can I estimate a Latent class multinomial (or conditional) logit using R? I have tried flexmix, poLCA, and they do not seem to support this model. thanks in advance adan -- View this message in context: http://r.789695.n4.nabble.com/Latent-class-multinomial-o

[R] Estimating a latent class multinomial logit regression with flexmix

I am trying to estimate a latent class multinomial logit regression with flexmix. I am not sure if I should do it as follows: m4<-flexmix(cbind(y,1-y)~x1+x2|id,model=FLXMRglm(family="binomial"),data=NPreg,k=2) , where id links each row with the corresponding respondent. Each respondent has 4 a