Estimating the parameters of the HMM | Maximum likelihood (ML) | Expectation Maximization (EM) or Baum-Welch algorithm | Bayesian estimation | Estimating the parameters of the multilevel HMM | Bayesian estimation of multilevel models | Multilevel model for the state-dependent probabilities $\boldsymbol{\theta}_{ki}$ | Multilevel model for the transition probability matrix $\boldsymbol{\Gamma_k}$ with transition probabilities $\boldsymbol{\gamma_{kij}}$ | Hybrid Metropolis within Gibbs sampler used to fit the multilevel HMM | Stepwise walkthrough of the used hybrid Metropolis within Gibbs sampler | Scaling the proposal distribution of the RW Metropolis sampler | Full conditional posterior distributions of the multilevel HMM | References

Introduction | Hidden Markov models | Multilevel hidden Markov models | Using the package mHMMbayes | A simple model | Starting values | Prior distributions | Fitting the model | Graphically displaying outcomes | Determining the number of hidden states | Determining the most likely state sequence | Checking model convergence and label switching | References