Consistency of LS estimators in the EV regression model with martingale difference errors

摘要

In this paper, we consider the following simple linear errors in variables model where , , x(1), x(2),...are unknown constants (parameters) and (i), (i), i=1, 2,...are observable. The consistency of the least square estimators for the unknown parameters and is established, while the errors { E-i}, {(i)} are sequences of martingale difference. In order to obtain our results, some limit theorems for weighted sums of martingale differences are proved.