| Home  | About ScienceAsia  | Publication charge  | Advertise with us  | Subscription for printed version  | Contact us  
Editorial Board
Journal Policy
Instructions for Authors
Online submission
Author Login
Reviewer Login
Volume 44 Number 6
Volume 44 Number 6
Volume 44 Number 6
Volume 44 Number 6
Volume 44 Number 5
Volume 44 Number 4
Earlier issues
Volume 43S Number 1 Volume 43 Number 1 Volume 43 Number 2

previous article 1

Research articles

ScienceAsia 43(2017): 56-60 |doi: 10.2306/scienceasia1513-1874.2017.43.056

Robust multivariate least angle regression

Hassan S. Uraibia,b,*, Habshah Midib,c, Sohel Ranab,d

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 PDF

37 Downloads 587 Views

a Department of Statistics, College of Administration and Economics, University of Al-Qadisiyah, 50082, Iraq
b Institute for Mathematical Research, University Putra Malaysia, 43400 UPM, Serdang, Malaysia
c Department of Mathematics, Faculty of Science, University Putra Malaysia, 43400 UPM, Serdang, Malaysia
d Department of Applied Statistics, Faculty of Sciences and Engineering, East West University, Aftabnagar, Dhaka-1212, Bangladesh

* Corresponding author, E-mail: hssn.sami1@gmail.com

Received 14 Jan 2016, Accepted 0 0000