The College of Science in the Department of Mathematics discussed a seminar entitled (Robust Multivariate Multiple Linear Regression: A Simulation Study and Applications) for postgraduate student Thamir W. H.. The seminar aims to introduce a robust version of Wilks' statistic for multivariate multiple linear regression, addressing the sensitivity of the classical Wilks' statistic to outliers. The proposed method utilizes MM-estimators and reweighted minimum covariance determinant (MCD) estimators, incorporating Hampel and Huber weight functions to enhance robustness.
