A General Class of Estimators for the Linear Regression Model Affected by Collinearity and Outliers |
| |
| Authors: | Pedro Macedo Manuel Scotto Elvira Silva |
| |
| Affiliation: | 1. Departamento de Matemática , Universidade de Aveiro, Campus Universitário de Santiago , Aveiro, Portugal pmacedo@ua.pt;3. Departamento de Matemática , Universidade de Aveiro, Campus Universitário de Santiago , Aveiro, Portugal;4. Faculdade de Economia , Universidade do Porto , Porto, Portugal |
| |
| Abstract: | In this article, a general class of estimators for the linear regression model affected by outliers and collinearity is introduced and studied in some detail. This class of estimators combines the theory of light, maximum entropy, and robust regression techniques. Our theoretical findings are illustrated through a Monte Carlo simulation study. |
| |
| Keywords: | Collinearity Linear regression Maximum entropy Outliers Robust regression |
|
|
