UPM Institutional Repository

Robust multivariate least angle regression


Citation

Uraibi, Hassan Sami and Midi, Habshah and Rana, Sohel (2017) Robust multivariate least angle regression. ScienceAsia, 43 (1). pp. 56-60. ISSN 1513-1874

Abstract

The least angle regression selection (LARS) algorithms that use the classical sample means, variances, and correlations between the original variables are very sensitive to the presence of outliers and other contamination. To remedy this problem, a simple modification of this algorithm is to replace the non-robust estimates with their robust counterparts. Khan, Van Aelst, and Zamar employed the robust correlation for winsorized data based on adjusted winsorization correlation as a robust bivariate correlation approach for plug-in LARS. However, the robust least angle regression selection has some drawbacks in the presence of multivariate outliers. We propose to incorporate the Olive and Hawkins reweighted and fast consistent high breakdown estimator into the robust plug-in LARS method based on correlations. Our proposed method is tested by using a numerical example and a simulation study.


Download File

[img]
Preview
Text (Abstract)
Robust multivariate least angle regression.pdf

Download (4kB) | Preview

Additional Metadata

Item Type: Article
Divisions: Faculty of Science
Institute for Mathematical Research
DOI Number: https://doi.org/10.2306/scienceasia1513-1874.2017.43.056
Publisher: Science Society of Thailand
Keywords: Variable selection; Least angle regression selection; RFCH; Adjusted winsorization
Depositing User: Mohd Hafiz Che Mahasan
Date Deposited: 16 Aug 2018 01:34
Last Modified: 28 Sep 2018 03:26
Altmetrics: http://www.altmetric.com/details.php?domain=psasir.upm.edu.my&doi=10.2306/scienceasia1513-1874.2017.43.056
URI: http://psasir.upm.edu.my/id/eprint/63147
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item