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...
| Autores: | , , |
|---|---|
| Tipo de documento: | artigo |
| Data de publicação: | 1995 |
| País: | España |
| Recursos: | Universitat Politècnica de Catalunya (UPC) |
| Repositório: | UPCommons. Portal del coneixement obert de la UPC |
| Idioma: | inglês |
| OAI Identifier: | oai:upcommons.upc.edu:2099/4056 |
| Acesso em linha: | https://hdl.handle.net/2099/4056 |
| Access Level: | Acceso aberto |
| Palavra-chave: | 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 |
| Resumo: | 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. |
|---|