المقارنة بين طريقتي المربعات الصغرى المعدلة و الانحرافات المطلقة الصغرى المعدلة لتقدير أنموذج الانحدار

Abstract EN

In this paper, we have relied on the two estimation methods, the fully modified least squares method and the fully modified olute deviations squares method, in estimating the parameters of the regression model when the explanatory variable is unstable and the limits of random error are self-related, which can be modeled according to one of the mixed models.

The research aims to make a comparison between the results of these two methods of estimation results in an attempt to reach the best method by relying on the MSE criterion and by adopting the simulation method as the results of the simulation experiment proved that the Fully modified least olute deviations method is better than Fully modified least square method