On the recursive solution of the normal equations of bilateral multivariate autoregressive models

A multivariate version of the bilateral autoregressive (AR) model is proposed, and a recursive algorithm is presented to solve the normal equations of the bilateral multivariate;IR models. The recursive algorithm is computationally efficient and easy to implement as a computer program, The recursive algorithm is useful for identifying and smoothing not only bilateral multivariate AR processes but multidimensional multivariate AR processes and multivariate spatio-temporal processes as well.