“…A multivariate ARMA model is given by the difference equation represents the input to the model which is a white Gaussian noise process having zero mean and covariance C, and n t R υ ∈ , which represents observation or modeling error, is also a random white noise process having covariance Q υ . Extending the approach of (Liang et al, 1993) to the multivariate case, assuming that N time samples of the output data are available, Equation (13) A and 0 B assumed to be identity matrices. In order to compose the input/output matrix , pq D , the unknown input signal t e needs to be estimated.…”