Thanks for the reply Christian,
> I have never used mmlcr for this, but quite generally when fitting such
> models, the likelihood has often very many local optima. This means that the
> result of the EM (or a similar) algorithm depends on the initialisation,
> which in flexmix (and perhaps also i
Dear Carson,
I have never used mmlcr for this, but quite generally when fitting such
models, the likelihood has often very many local optima. This means that
the result of the EM (or a similar) algorithm depends on the
initialisation, which in flexmix (and perhaps also in mmlcr) is done in a
Dear list,
I have been comparing the outputs of two packages for latent class
regression, namely 'flexmix', and 'mmlcr'. What I have noticed is that
the flexmix package appears to come up with a much better fit than the
mmlcr package (based on logLik, AIC, BIC, and visual inspection). Has
anyone e
Dear Rita,
The depmixS4 package handles such models. It is still in beta testing
so I would
appreciate it if you share your experiences with it. Also let me know
if you have
further questions.
Best, Ingmar
On 16 Mar 2009, at 10:19, Rita Gaio wrote:
Dear R users,
I want to apply latent
Dear R users,
I want to apply latent class models (mixture models) with covariates in the
case of continuous and categorical variables. My questions are the follow:
a) the only package in R that can handle mixture models with data of mixed
type is moc (which unfortunately was left orphaned recent
5 matches
Mail list logo