توظيف اسلوب مقدرات MM في تقدير نموذج انحدار المكونات الرئيسية : دراسة مقارنة

Abstract EN

This paper focuses on proposing the use of robust MM estimators in estimating the parameters of the principal component regression model, which is usually used in estimating the regression model when the explanatory variables are not independent.

even in the presence of leverage points in the data and gives estimators with good efficiency, this estimator has been called the MM estimator, referring to the fact that more than one M estimator is used to obtain the final estimator as the estimation is done using the Iteratively Re-weighted Least Square (IRLS) method.

The classical and the proposed models will be applied to data obtained from the cement factory in Badoush.

On this basis, a comparison between the known classical methods (the least squares method was used for the purpose of comparison) and the suggested method using MM estimators will be made through two experimental studies using simulation and application of cement factory data.