Data-based labelling
This function reorders the MCMC output according the data-based relabelling algorithm of Rodriguez and Walker (2014). The idea is to define a loss function which resembles a k-means type diveging measure of cluster centers. After the cluster centers have been estimated, the algorithm finds the optimal permutations that switch every simulated MCMC sample to them.
dataBased(x, K, z)
x |
n-dimensional data vector/array. |
K |
the number of mixture components. |
z |
m\times n integer array of the latent allocation vectors generated from an MCMC algorithm. |
permutations |
m\times K dimensional array of permutations |
Panagiotis Papastamoulis
Rodriguez C.E. and Walker S. (2014). Label Switching in Bayesian Mixture Models: Deterministic relabeling strategies. Journal of Computational and Graphical Statistics. 23:1, 25-45
#load a toy example: MCMC output consists of the random beta model
# applied to a normal mixture of \code{K=2} components. The number of
# observations is equal to \code{n=5}. The number of MCMC samples is
# equal to \code{m=300}. The 1000 generated MCMC samples are stored
#to array mcmc.pars.
data("mcmc_output")
z<-data_list$"z"
K<-data_list$"K"
x<-data_list$"x"
mcmc.pars<-data_list$"mcmc.pars"
# mcmc parameters are stored to array \code{mcmc.pars}
# mcmc.pars[,,1]: simulated means of the two components
# mcmc.pars[,,2]: simulated variances of the two components
# mcmc.pars[,,3]: simulated weights of the two components
# Apply dataBased relabelling
run<-dataBased(x = x, K = K, z = z)
# apply the permutations returned by typing:
reordered.mcmc<-permute.mcmc(mcmc.pars,run$permutations)
# reordered.mcmc[,,1]: reordered means of the two components
# reordered.mcmc[,,2]: reordered variances of the components
# reordered.mcmc[,,3]: reordered weightsPlease choose more modern alternatives, such as Google Chrome or Mozilla Firefox.