Thanks for the book suggestion. I'll check it out tomorrow when the library opens up.
Yes, it is a multilevel model, but its likelihood function is the sum of the likelihood functions for the individual levels (i.e. a simple multinomial logits) and some other terms (the priors). It is, essentially, the hierarchical priors model of Finkel and Manning (HLT, 2009). So to compute the above composite likelihood function I need just the simple multinomial logit likelihood for each of the separate pools (there are just two levels - the lower consisting of 4 pools, the upper of just one, i.e. it's a hierarchical relationship). So I am really surprised that I could not find R package containing a function that computes the simple multinomial logit regression for a given set of parameter values (rather than simply supplying the final fit). statquant wrote: > > > Hi: John Fox's CAR book has some very nice examples of how the > multinomial > likelihood is estimated computationally speaking. But you mentioned > multilevel earlier which sounds more complex ? > > -- View this message in context: http://www.nabble.com/Likelihood-Function-for-Multinomial-Logistic-Regression-and-its-partial-derivatives-tp24772731p24783615.html Sent from the R help mailing list archive at Nabble.com. ______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
