PARAMETER-ESTIMATION IN REGRESSION-MODELS WITH AUTOCORRELATED ERRORS USING IRREGULAR DATA

We consider the least squares and the Gaussian maximum likelihood estimators in the regression model with stochastic explanatory variables and autocorrelated errors, possibly nonnormal, in the situation where data contain irregular observations or missing values. We establish the weak consistency and asymptotic normality of the estimators. We compare the efficiency of the least squares estimator of the regression parameter to that of the maximum likelihood estimator for a special case of the model.