Re: [R] bayesian mixed logit

Carlo F uea.ac.uk> writes: > I am tryin on simulated data, say 300 repondents, 8 choice per person, only > 2 random parameters... so i think it should be well behaved... so I am > probably doing a mistake! > > Thank for poiting out the MCMCglmm package, ultimately I need to write my > own non-l

Re: [R] bayesian mixed logit

Thanks Ben, I am tryin on simulated data, say 300 repondents, 8 choice per person, only 2 random parameters... so i think it should be well behaved... so I am probably doing a mistake! :-) Thank for poiting out the MCMCglmm package, ultimately I need to write my own non-linear untility function,

Re: [R] bayesian mixed logit

Carlo Fezzi (ENV uea.ac.uk> writes: > > Dear all, > > I am writing an R code to fit a Bayesian mixed logit (BML) via MCMC / MH algorithms following Train (2009, ch. 12). > > Unfortunately, after many draws the covariance matrix > of the correlated random parameters tend to become > a matrix w

[R] bayesian mixed logit

Dear all, I am writing an R code to fit a Bayesian mixed logit (BML) via MCMC / MH algorithms following Train (2009, ch. 12). Unfortunately, after many draws the covariance matrix of the correlated random parameters tend to become a matrix with almost perfect correlation, so I think there is a