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

Sira Allende; Carlos Bouza; Isidro Romero

Qüestiió (1995)

  • Volume: 19, Issue: 1-2-3, page 107-121
  • ISSN: 0210-8054

Abstract

top
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.

How to cite

top

Allende, Sira, Bouza, Carlos, and Romero, Isidro. "Fitting a linear regression model by combining least squares and least absolute value estimation.." Qüestiió 19.1-2-3 (1995): 107-121. <http://eudml.org/doc/40235>.

@article{Allende1995,
abstract = {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.},
author = {Allende, Sira, Bouza, Carlos, Romero, Isidro},
journal = {Qüestiió},
keywords = {Regresión lineal; Ajuste de superficies; Estimadores robustos; Datos atípicos; Modelos paramétricos; Regresión múltiple; outliers in regression; regression; bicriteria parametric algorithm},
language = {eng},
number = {1-2-3},
pages = {107-121},
title = {Fitting a linear regression model by combining least squares and least absolute value estimation.},
url = {http://eudml.org/doc/40235},
volume = {19},
year = {1995},
}

TY - JOUR
AU - Allende, Sira
AU - Bouza, Carlos
AU - Romero, Isidro
TI - Fitting a linear regression model by combining least squares and least absolute value estimation.
JO - Qüestiió
PY - 1995
VL - 19
IS - 1-2-3
SP - 107
EP - 121
AB - 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.
LA - eng
KW - Regresión lineal; Ajuste de superficies; Estimadores robustos; Datos atípicos; Modelos paramétricos; Regresión múltiple; outliers in regression; regression; bicriteria parametric algorithm
UR - http://eudml.org/doc/40235
ER -

NotesEmbed ?

top

You must be logged in to post comments.