Xia, Yemao; Chen, Gaoyan; Liu, Ying’an Robust inferences on the hidden Markov latent variable models based on the multivariate \(t\)-distribution. (Chinese. English summary) Zbl 1374.62102 J. Syst. Sci. Math. Sci. 36, No. 10, 1783-1803 (2016). Summary: Latent variable models play an important role in characterizing interrelationships among factor variables and constructing relationships between factors and observed variables. However, in real applications, data often have the heavy tails and/or contain extreme values. In this paper, we extend the classic latent variable model to the dynamic latent variable model mixed with homogenous hidden Markov model and establish maximum likelihood analysis procedure based on the multivariate \(t\)-distribution. The empirical results show that our proposed methodology is effective to down weight the influence of the outliers. MSC: 62M05 Markov processes: estimation; hidden Markov models 62F35 Robustness and adaptive procedures (parametric inference) Keywords:hidden Markov model; latent variable model; expectation-maximization; forward-backward recursion PDFBibTeX XMLCite \textit{Y. Xia} et al., J. Syst. Sci. Math. Sci. 36, No. 10, 1783--1803 (2016; Zbl 1374.62102)