ABSTRACT
In this chapter, we deal with miscellaneous advanced topics about latent Markov (LM) models. First of all, we introduce models for continuous responses, formulating assumptions on either the conditional mean or a conditional quantile of the distribution of the response variable, given the corresponding covariates and latent variables. Then, we discuss how to deal with missing responses and we detail better certain computational issues: the Newton-Raphson (NR) algorithm for computing maximum likelihood estimates of the parameters and the parametric bootstrap to obtain the corresponding standard errors.
