ON MAXIMUM-LIKELIHOOD-ESTIMATION OF DIFFERENCE EQUATION PARAMETERS

This correspondence is prompted by a recent paper in the TRANSACTIONS ON SIGNAL PROCESSING, which discussed the maximum likelihood (ML) esti mation of difference equation parameters in a flawed manner. The corre ct ML parameter estimate is derived herein by means of a high level ar gument based on the invariance principle as well as by a direct calcul ation. Contrary to what is suggested in the aforementioned paper, all ML based order estimation procedures (such as AIC or GAIC rules) yield results that do not depend on the normalizing constraint imposed on t he parameter vector.