Enhancement of partial robust M-regression (PRM) performance using Bisquare weight function

Partial Least Squares (PLS) regression is a popular regression technique for handling multicollinearity in low and high dimensional data which fits a linear relationship between sets of explanatory and response variables. Several robust PLS methods are proposed to accommodate the classical PLS algor...

Full description

Bibliographic Details
Published in:AIP Conference Proceedings
Main Author: Mohamad M.; Ramli N.M.; Mamat N.A.M.; Ahmad S.
Format: Conference paper
Language:English
Published: American Institute of Physics Inc. 2014
Online Access:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85010868513&doi=10.1063%2f1.4894338&partnerID=40&md5=cac4c0bef273110a6e6a846df8637ee9
id 2-s2.0-85010868513
spelling 2-s2.0-85010868513
Mohamad M.; Ramli N.M.; Mamat N.A.M.; Ahmad S.
Enhancement of partial robust M-regression (PRM) performance using Bisquare weight function
2014
AIP Conference Proceedings
1613

10.1063/1.4894338
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85010868513&doi=10.1063%2f1.4894338&partnerID=40&md5=cac4c0bef273110a6e6a846df8637ee9
Partial Least Squares (PLS) regression is a popular regression technique for handling multicollinearity in low and high dimensional data which fits a linear relationship between sets of explanatory and response variables. Several robust PLS methods are proposed to accommodate the classical PLS algorithms which are easily affected with the presence of outliers. The recent one was called partial robust M-regression (PRM). Unfortunately, the use of monotonous weighting function in the PRM algorithm fails to assign appropriate and proper weights to large outliers according to their severity. Thus, in this paper, a modified partial robust M-regression is introduced to enhance the performance of the original PRM. A re-descending weight function, known as Bisquare weight function is recommended to replace the fair function in the PRM. A simulation study is done to assess the performance of the modified PRM and its efficiency is also tested in both contaminated and uncontaminated simulated data under various percentages of outliers, sample sizes and number of predictors. © 2014 AIP Publishing LLC.
American Institute of Physics Inc.
0094243X
English
Conference paper

author Mohamad M.; Ramli N.M.; Mamat N.A.M.; Ahmad S.
spellingShingle Mohamad M.; Ramli N.M.; Mamat N.A.M.; Ahmad S.
Enhancement of partial robust M-regression (PRM) performance using Bisquare weight function
author_facet Mohamad M.; Ramli N.M.; Mamat N.A.M.; Ahmad S.
author_sort Mohamad M.; Ramli N.M.; Mamat N.A.M.; Ahmad S.
title Enhancement of partial robust M-regression (PRM) performance using Bisquare weight function
title_short Enhancement of partial robust M-regression (PRM) performance using Bisquare weight function
title_full Enhancement of partial robust M-regression (PRM) performance using Bisquare weight function
title_fullStr Enhancement of partial robust M-regression (PRM) performance using Bisquare weight function
title_full_unstemmed Enhancement of partial robust M-regression (PRM) performance using Bisquare weight function
title_sort Enhancement of partial robust M-regression (PRM) performance using Bisquare weight function
publishDate 2014
container_title AIP Conference Proceedings
container_volume 1613
container_issue
doi_str_mv 10.1063/1.4894338
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85010868513&doi=10.1063%2f1.4894338&partnerID=40&md5=cac4c0bef273110a6e6a846df8637ee9
description Partial Least Squares (PLS) regression is a popular regression technique for handling multicollinearity in low and high dimensional data which fits a linear relationship between sets of explanatory and response variables. Several robust PLS methods are proposed to accommodate the classical PLS algorithms which are easily affected with the presence of outliers. The recent one was called partial robust M-regression (PRM). Unfortunately, the use of monotonous weighting function in the PRM algorithm fails to assign appropriate and proper weights to large outliers according to their severity. Thus, in this paper, a modified partial robust M-regression is introduced to enhance the performance of the original PRM. A re-descending weight function, known as Bisquare weight function is recommended to replace the fair function in the PRM. A simulation study is done to assess the performance of the modified PRM and its efficiency is also tested in both contaminated and uncontaminated simulated data under various percentages of outliers, sample sizes and number of predictors. © 2014 AIP Publishing LLC.
publisher American Institute of Physics Inc.
issn 0094243X
language English
format Conference paper
accesstype
record_format scopus
collection Scopus
_version_ 1814778510353367040