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

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 e...

Descripción completa

Detalles Bibliográficos
Autores: Allende, Sira, Bouza, Carlos, Romero, Isidro
Tipo de recurso: artículo
Fecha de publicación:1995
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2099/4056
Acceso en línea:https://hdl.handle.net/2099/4056
Access Level:acceso abierto
Palabra clave:Inference
Outliers in regression
L1 regression
Bicriterion parametric algorithm
Inferència
Classificació AMS::62 Statistics::62F Parametric inference
Classificació AMS::62 Statistics::62J Linear inference, regression
Descripción
Sumario: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.