Comparación de la regresión GINI con la regresión de mínimos cuadrados ordinarios y otros modelos de regresión lineal robustos

In this paper compares Gini regression (using the non-parametric approach of weighted average of slope, instead of the parametric approach) with OLS and other robust regression methods, the type L (LAV, linear combinations of order statistics), the type M (M Huber, based on the concept of maximum likelihood) and the type MM (based on the minimization of an estimator M). The comparison of the methods is performed via simulation under different scenarios. The results show that the Gini regression has a higher degree of robustness compared with the OLS regression to estimate the regression coefficients in the presence of outliers, but their robustness is less than robust estimation methods LAV, M Huber and MM.

• Autores: Correa Morales, Juan Carlos; Florez, Gloria Patricia Carmona
• Fecha de publicación: 2015
• Institución: Universidad Santo Tomás
• Repositorio: Repositorio Institucional USTA
• Idioma: spa
• OAI Identifier: oai:repository.usta.edu.co:11634/39595
• Acceso en línea: https://revistas.usantotomas.edu.co/index.php/estadistica/article/view/1186; http://hdl.handle.net/11634/39595
• Palabra clave: Datos atípicos; eficiencia; míminos cuadrados ordinarios; modelos de regresión robustos; regresión Gini; robustez.
• License: http://purl.org/coar/access_right/c_abf2