Year: 2005
Type: preprint
Abstract: The detection of influential observations for the standard least squares regression model is a question that has been extensively studied. LAD regression diagnostics offers alternative approaches whose main feature is the robustness. In this paper a new approach for nonparametric detection of influencial observations in LAD regression models is presented and compared with other classical methods of diagnostics.
Source: arXiv (Cornell University)
Authors: Melfi, Giuseppe, Faria, Susana
Institutions: University of Minho, University of Neuchâtel
Language: English
Subfield: Statistics and Probability
Field: Mathematics
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W1635150667