A NOTE ON THE MAXIMUM LIKELIHOOD ESTIMATION OF REGRESSION MODELS WITH FIRST ORDER MOVING AVERAGE ERRORS WITH ROOTS ON THE UNIT CIRCLE

This note gives an alternative derivation of Sargan and Bhargava' s results concerning the probability of observing on the unit circle a local maximum of the likelihood function of regression models with first order moving average errors. The note also discusses the relevance of these results for the computation of the exact maximum likelihood estimation of regression models with moving average errors.