Remove the label switching phenomenon from the MCMC samples of Bayesian mixtures of Plackett-Luce models with a different number of components.
label_switchPLMIX_single(pi_inv, G, MCMCsampleP, MCMCsampleW, MAPestP, MAPestW)A list of named objects:
final_samplePNumeric \(G\)\(\times\)\(K\)\(\times\)\(L\) array MCMC samples of the component-specific support parameters adjusted for label switching.
final_sampleWNumeric \(L\)\(\times\)\(G\) matrix of MCMC samples of the mixture weights adjusted for label switching.
An object of class top_ordering, collecting the numeric \(N\)\(\times\)\(K\) data matrix of partial orderings, or an object that can be coerced with as.top_ordering.
Number of mixture components.
Numeric \(L\)\(\times\)\(G*K\) matrix with the MCMC samples of the component-specific support parameters to be processed.
Numeric \(L\)\(\times\)\(G\) matrix with the MCMC samples of the mixture weights to be processed.
Numeric \(G\)\(\times\)\(K\) matrix of MAP component-specific support parameter estimates to be used as pivot in the PRA method.
Numeric vector of the \(G\) MAP estimates of the mixture weights as pivot in the PRA method.
Cristina Mollica and Luca Tardella
The label_switchPLMIX function performs the label switching adjustment of the MCMC samples via the Pivotal Reordering Algorithm (PRA) described in Marin et al (2005), by recalling the pra function from the label.switching package.