Stores the output of Bayesian model selection for mixture models,
e.g. as produced by function bfnormmix.
Methods are provided for retrieving the posterior probability of a given number of mixture components, posterior means and posterior samples of the mixture model parameters.
Typically objects are automatically created by a call to bfnormmix.
The class has the following slots:
data.frame containing posterior probabilities for different numbers of components (k) and log-posterior probability of a component being empty (contain no individuals)
Number of variables in the data to which the model was fit
Number of observations in the data to which the model was fit
Prior parameters used when fitting the model
Posterior parameters for a 1-component mixture, e.g. for a Normal mixture the posterior is N(mu1,Sigma/prec) IW(nu1,S1)
For each considered value of k, posterior samples for the parameters of the k-component model are stored
Computes posterior means for all parameters
signature(object = "mixturebf"): Displays general
information about the object.
signature(object = "mixturebf"): Extracts
posterior model probabilities, Bayes factors and posterior
probability of a cluster being empty
signature(object = "mixturebf"): Extracts
posterior samples
David Rossell
Fuquene J., Steel M.F.J., Rossell D. On choosing mixture components via non-local priors. 2018. arXiv
See also bfnormmix