Abstract: | Multivariate Markov chain models have previously been proposed in for studyingdependent multiple categorical data sequences. For a given multivariate Markovchain model, an important problem is to study its joint stationary distribution. In thispaper, we use two techniques to present some perturbation bounds for the joint stationarydistribution vector of a multivariate Markov chain with s categorical sequences.Numerical examples demonstrate the stability of the model and the effectiveness of ourperturbation bounds. |