Robust linear model selection in high dimensional data

• Author(s): Shahriari, Shirin ; Faria, Susana ; Gonçalves, A. Manuela
• Date: 2013
• Persistent ID: https://hdl.handle.net/1822/27168
• Origin: RepositóriUM - Universidade do Minho
• Subject(s): Robust linear regression; Robust variable selection; Outliers
• Document Type: Other
• Language: English
• Contributor(s): Universidade do Minho

Description

In this work we consider the problem of selecting variables from a potentially large number of predictors in a regression model when outliers and atypical observations are embedded in data. Since classical variable selection methods are not resistant to the presence of outliers and other contaminations, well established robust variable selection methods in high dimensional data sets are studied. Different simulation scenarios will be carried out to compare the performance of these methods.