Robust linear discriminant rules with coordinatewise and distance based approaches

Linear discriminant analysis (LDA) is one of the supervised classification techniques to deal with relationship between a categorical variable and a set of continuous variables. The main objective of LDA is to create a function to distinguish between groups and allocating future observations to prev...

Full description

Saved in:

Bibliographic Details
Main Author:	Lim, Yai Fung
Format:	Thesis
Language:	eng eng eng
Published:	2020
Subjects:	QA299.6-433 Analysis
Online Access:	https://etd.uum.edu.my/8799/1/Deposit%20Permission_s900800.pdf https://etd.uum.edu.my/8799/2/s900800_01.pdf https://etd.uum.edu.my/8799/3/s900800_references.docx
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-uum-etd.8799
record_format	uketd_dc
spelling	my-uum-etd.87992021-11-14T07:40:22Z Robust linear discriminant rules with coordinatewise and distance based approaches 2020 Lim, Yai Fung Syed Yahaya, Sharipah Ali, Hazlina Awang Had Salleh Graduate School of Arts & Sciences Awang Had Salleh Graduate School of Arts & Sciences QA299.6-433 Analysis Linear discriminant analysis (LDA) is one of the supervised classification techniques to deal with relationship between a categorical variable and a set of continuous variables. The main objective of LDA is to create a function to distinguish between groups and allocating future observations to previously defined groups. Under the assumptions of normality and homoscedasticity, the LDA yields optimal linear discriminant rule (LDR) between two or more groups. However, the optimality of LDA highly relies on the sample mean and sample covariance matrix which are known to be sensitive to outliers. To abate these conflicts, robust location and scale estimators via coordinatewise and distance based approaches have been applied in constructing new robust LDA. These robust estimators were used to replace the classical sample mean and sample covariance to form robust linear discriminant rules (RLDR). A total of six RLDR, namely four coordinatewise (RLDRM, RLDRMw, RLDRW, RLDRWw) and two distance based (RLDRV, RLDRT) approaches have been proposed and implemented in this study. Simulation and real data study were conducted to investigate on the performance of the proposed RLDR, measured in terms of misclassification error rates and computational time. Several data conditions such as non-normality, heteroscedasticity, balanced and unbalanced data set were manipulated in the simulation study to evaluate the performance of these proposed RLDR. In real data study, a set of diabetes data was used. This data set violated the assumptions of normality as well as homoscedasticity. The results showed that the novel RLDRV is the best proposed RLDR to solve classification problem since it provides as much as 91.03% accuracy in classification as shown in the real data study. The proposed RLDR are good alternatives to the classical LDR as well as existing RLDR since these RLDR perform well in classification problems even under contaminated data. 2020 Thesis https://etd.uum.edu.my/8799/ https://etd.uum.edu.my/8799/1/Deposit%20Permission_s900800.pdf text eng staffonly https://etd.uum.edu.my/8799/2/s900800_01.pdf text eng public https://etd.uum.edu.my/8799/3/s900800_references.docx text eng public other doctoral Universiti Utara Malaysia
institution	Universiti Utara Malaysia
collection	UUM ETD
language	eng eng eng
advisor	Syed Yahaya, Sharipah Ali, Hazlina
topic	QA299.6-433 Analysis
spellingShingle	QA299.6-433 Analysis Lim, Yai Fung Robust linear discriminant rules with coordinatewise and distance based approaches
description	Linear discriminant analysis (LDA) is one of the supervised classification techniques to deal with relationship between a categorical variable and a set of continuous variables. The main objective of LDA is to create a function to distinguish between groups and allocating future observations to previously defined groups. Under the assumptions of normality and homoscedasticity, the LDA yields optimal linear discriminant rule (LDR) between two or more groups. However, the optimality of LDA highly relies on the sample mean and sample covariance matrix which are known to be sensitive to outliers. To abate these conflicts, robust location and scale estimators via coordinatewise and distance based approaches have been applied in constructing new robust LDA. These robust estimators were used to replace the classical sample mean and sample covariance to form robust linear discriminant rules (RLDR). A total of six RLDR, namely four coordinatewise (RLDRM, RLDRMw, RLDRW, RLDRWw) and two distance based (RLDRV, RLDRT) approaches have been proposed and implemented in this study. Simulation and real data study were conducted to investigate on the performance of the proposed RLDR, measured in terms of misclassification error rates and computational time. Several data conditions such as non-normality, heteroscedasticity, balanced and unbalanced data set were manipulated in the simulation study to evaluate the performance of these proposed RLDR. In real data study, a set of diabetes data was used. This data set violated the assumptions of normality as well as homoscedasticity. The results showed that the novel RLDRV is the best proposed RLDR to solve classification problem since it provides as much as 91.03% accuracy in classification as shown in the real data study. The proposed RLDR are good alternatives to the classical LDR as well as existing RLDR since these RLDR perform well in classification problems even under contaminated data.
format	Thesis
qualification_name	other
qualification_level	Doctorate
author	Lim, Yai Fung
author_facet	Lim, Yai Fung
author_sort	Lim, Yai Fung
title	Robust linear discriminant rules with coordinatewise and distance based approaches
title_short	Robust linear discriminant rules with coordinatewise and distance based approaches
title_full	Robust linear discriminant rules with coordinatewise and distance based approaches
title_fullStr	Robust linear discriminant rules with coordinatewise and distance based approaches
title_full_unstemmed	Robust linear discriminant rules with coordinatewise and distance based approaches
title_sort	robust linear discriminant rules with coordinatewise and distance based approaches
granting_institution	Universiti Utara Malaysia
granting_department	Awang Had Salleh Graduate School of Arts & Sciences
publishDate	2020
url	https://etd.uum.edu.my/8799/1/Deposit%20Permission_s900800.pdf https://etd.uum.edu.my/8799/2/s900800_01.pdf https://etd.uum.edu.my/8799/3/s900800_references.docx
_version_	1747828463437348864

Robust linear discriminant rules with coordinatewise and distance based approaches

Similar Items