Besides multicollinearity, outliers also constitute a problem in the multiple linear regression analysis. We propose three new estimators of the robust ridge regression in the presence of multicollinearity and outliers, which called the Ridge Least Trimmed Squares, Ridge MM and Ridge Least Absolute Value estimator .For this purpose, a simulation study is conducted in order to see the difference between the proposed methods and the existing methods in terms of their effectiveness measured by the mean squares error. The performances of the proposed methods are examined for different percentages of outliers and different degrees of multicollinearity. The results show that the proposed estimators are better than six of the existing methods in the presence of multicollinearity and outliers.
Karosa, A. (2019). A comparative study of some of the robust Ridge regression capabilities.. Journal of Alexandria University for Administrative Sciences, 56(1), 187-214. doi: 10.21608/acj.2019.35643
MLA
Ahmed Karosa. "A comparative study of some of the robust Ridge regression capabilities.", Journal of Alexandria University for Administrative Sciences, 56, 1, 2019, 187-214. doi: 10.21608/acj.2019.35643
HARVARD
Karosa, A. (2019). 'A comparative study of some of the robust Ridge regression capabilities.', Journal of Alexandria University for Administrative Sciences, 56(1), pp. 187-214. doi: 10.21608/acj.2019.35643
VANCOUVER
Karosa, A. A comparative study of some of the robust Ridge regression capabilities.. Journal of Alexandria University for Administrative Sciences, 2019; 56(1): 187-214. doi: 10.21608/acj.2019.35643
)
مشاهدة على SCiNiTO