Transform time series (Markov chain) data with several states/categories into the required Njk.i-structure containing the transition frequencies between these states/categories.
Plots paths of all sorts of likelihood and (prior) densities, like the log-likelihood, log posterior density, log classification likelihood and the entropy all including markings for the position of the maximum value, and further log prior densities for η, β, ξ and e (depending on availability/model type).
This function provides Bayesian multinomial logit regression using auxiliary mixture sampling. See Fruehwirth-Schnatter and Fruehwirth (2010). That is an MCMC sampler that is also used for the mixtures-of-experts extension of Dirichlet Multinomial (dmClustExtended) and Markov chain clustering (mcClustExtended). It requires four mandatory arguments: Data, Prior, Initial and Mcmc; each representing a list of (mandatory) arguments: Data contains data information, Prior contains prior information, Initial contains information about starting conditions (initial values) and Mcmc contains the setup for the MCMC sampler.
This function provides Markov chain clustering with or without multinomial logit model (mixtures-of-experts) extension (see References). That is an MCMC sampler for the mixtures-of-experts extension of Markov chain clustering. It requires four mandatory arguments: Data, Prior, Initial and Mcmc; each representing a list of (mandatory) arguments: Data contains data information, Prior contains prior information, Initial contains information about starting conditions (initial values) and Mcmc contains the setup for the MCMC sampler.
This function provides Dirichlet Multinomial Clustering with or without multinomial logit model (mixtures-of-experts) extension (see References). That is an MCMC sampler for the mixtures-of-experts extension of Dirichlet Multinomial clustering. It requires four mandatory arguments: Data, Prior, Initial and Mcmc; each representing a list of (mandatory) arguments: Data contains data information, Prior contains prior information, Initial contains information about starting conditions (initial values) and Mcmc contains the setup for the MCMC sampler.
Calculates the posterior expectation of the variance of the individual transition probabilities as well as posterior expectation and standard deviation of the row-specific unobserved heterogeneity measure in each group to analyse how much unobserved heterogeneity is present in the various clusters (see Pamminger and Fruehwirth-Schnatter (2010) in References).
Calculates the posterior expectation and standard deviations of the average cluster-specific transition matrices and also offers some other analyses like plotting paths of MCMC draws.