Development of robust <scp>Özkale–Kaçiranlar</scp> and <scp>Yang–Chang</scp> estimators for regression models in the presence of multicollinearity and outliers
Fuad A. Awwad, İssam Dawoud, Mohamed R. Abonazel
Abstract
Abstract The ordinary least‐squares estimator is commonly used to estimate the parameters of a linear regression model but gives unreliable and unfavorable results when two problems occur together: multicollinearity and outliers. This article proposes two different robust estimators of the regression parameters to cope with these problems together. The proposed estimators are a robust version of the Özkale–Kaçiranlar and Yang–Chang estimators. Theoretical calculations, numerical simulations, and real‐life data on manufacturing production are presented to demonstrate the superiority of the proposed robust estimators to existing estimators at dealing with multicollinearity and outliers at the same time.