adanmartinez
2011-Dec-21 02:16 UTC
[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 alternatives to chose from. y takes the value 1 only for the alternative chosen; x1 and x2 are alternative-specific variables (thus they take different values in each row) I will much appreciate your help. thanks in advance -- View this message in context: http://r.789695.n4.nabble.com/Estimating-a-latent-class-multinomial-logit-regression-with-flexmix-tp4220219p4220219.html Sent from the R help mailing list archive at Nabble.com.