Fitting a linear regression model by combining least squares and least absolute value estimation.
Allende, Sira ; Bouza, Carlos ; Romero, Isidro
Qüestiió, Tome 19 (1995), p. 107-121 / Harvested from Biblioteca Digital de Matemáticas
Access to full text

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.

Publié le : 1995-01-01
DMLE-ID : 2876 
@article{urn:eudml:doc:40235,
     title = {Fitting a linear regression model by combining least squares and least absolute value estimation.},
     journal = {Q\"uestii\'o},
     volume = {19},
     year = {1995},
     pages = {107-121},
     mrnumber = {MR1376780},
     zbl = {1167.62443},
     language = {en},
     url = {http://dml.mathdoc.fr/item/urn:eudml:doc:40235}
}

Allende, Sira; Bouza, Carlos; Romero, Isidro. Fitting a linear regression model by combining least squares and least absolute value estimation.. Qüestiió, Tome 19 (1995) pp. 107-121. http://gdmltest.u-ga.fr/item/urn:eudml:doc:40235/