Resumen de Fitting a linear regression model by combining least squares and least absolute value estimation

Sira Allende Alonso, Carlos N. Bouza, Isidro Romero

• Robust estimation of the multiple regression is modeled by using a convex combination of Least Squares and Least Absolute Value criterions. A Bicriterion Parametric algorithm is developed for computing the corresponding estimates. The proposed procedure should be specially useful when outliers are expected. Its behavior is analyzed using some examples