A multivariate hidden Markov model: prospects for the course of public trust in Poland

We propose a multivariate Hidden Markov Model (HMM) to analyse longitudinal survey data able to ac- count for repeated responses over time along with longitudinal survey weights and missing responses. Since trust may be conceived as a psychological unobservable process of each person that fluctuates over time we consider observed time-varying and time-fixed individual covariates influencing the initial and transition prob- abilities. We employ the joint estimated posterior probabilities to make predictions on the latent trajectories of the course of public trust of the Polish society.