Cover Image

Robust linear discriminant models to solve financial crisis in banking sectors

Linear discriminant analysis (LDA) is a widely-used technique in patterns classification via an equation which will minimize the probability of misclassifying cases into their respective categories.However, the performance of classical estimators in LDA highly depends on the assumptions of normality...

Full description

Saved in:
Bibliographic Details
Main Authors: Lim, Yai-Fung, Syed Yahaya, Sharipah Soaad, Idris, Faoziah, Ali, Hazlina, Omar, Zurni
Format: Conference or Workshop Item
Published: 2014
Subjects:
HG Finance
Online Access:http://repo.uum.edu.my/16532/
http://doi.org/10.1063/1.4903673
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.uum.repo.16532
record_format eprints
spelling my.uum.repo.165322016-05-19T02:59:33Z http://repo.uum.edu.my/16532/ Robust linear discriminant models to solve financial crisis in banking sectors Lim, Yai-Fung Syed Yahaya, Sharipah Soaad Idris, Faoziah Ali, Hazlina Omar, Zurni HG Finance Linear discriminant analysis (LDA) is a widely-used technique in patterns classification via an equation which will minimize the probability of misclassifying cases into their respective categories.However, the performance of classical estimators in LDA highly depends on the assumptions of normality and homoscedasticity. Several robust estimators in LDA such as Minimum Covariance Determinant (MCD), S-estimators and Minimum Volume Ellipsoid (MVE) are addressed by many authors to alleviate the problem of non-robustness of the classical estimates. In this paper, we investigate on the financial crisis of the Malaysian banking institutions using robust LDA and classical LDA methods. Our objective is to distinguish the "distress" and "non-distress" banks in Malaysia by using the LDA models. Hit ratio is used to validate the accuracy predictive of LDA models. The performance of LDA is evaluated by estimating the misclassification rate via apparent error rate. The results and comparisons show that the robust estimators provide a better performance than the classical estimators for LDA 2014 Conference or Workshop Item PeerReviewed Lim, Yai-Fung and Syed Yahaya, Sharipah Soaad and Idris, Faoziah and Ali, Hazlina and Omar, Zurni (2014) Robust linear discriminant models to solve financial crisis in banking sectors. In: 3rd International Conference on Quantitative Sciences and its Applications (ICOQSIA 2014), 12–14 August 2014, Langkawi, Kedah Malaysia. http://doi.org/10.1063/1.4903673 doi:10.1063/1.4903673
institution Universiti Utara Malaysia
building UUM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Utara Malaysia
content_source UUM Institutionali Repository
url_provider http://repo.uum.edu.my/
topic HG Finance
spellingShingle HG Finance
Lim, Yai-Fung
Syed Yahaya, Sharipah Soaad
Idris, Faoziah
Ali, Hazlina
Omar, Zurni
Robust linear discriminant models to solve financial crisis in banking sectors
description Linear discriminant analysis (LDA) is a widely-used technique in patterns classification via an equation which will minimize the probability of misclassifying cases into their respective categories.However, the performance of classical estimators in LDA highly depends on the assumptions of normality and homoscedasticity. Several robust estimators in LDA such as Minimum Covariance Determinant (MCD), S-estimators and Minimum Volume Ellipsoid (MVE) are addressed by many authors to alleviate the problem of non-robustness of the classical estimates. In this paper, we investigate on the financial crisis of the Malaysian banking institutions using robust LDA and classical LDA methods. Our objective is to distinguish the "distress" and "non-distress" banks in Malaysia by using the LDA models. Hit ratio is used to validate the accuracy predictive of LDA models. The performance of LDA is evaluated by estimating the misclassification rate via apparent error rate. The results and comparisons show that the robust estimators provide a better performance than the classical estimators for LDA
format Conference or Workshop Item
author Lim, Yai-Fung
Syed Yahaya, Sharipah Soaad
Idris, Faoziah
Ali, Hazlina
Omar, Zurni
author_facet Lim, Yai-Fung
Syed Yahaya, Sharipah Soaad
Idris, Faoziah
Ali, Hazlina
Omar, Zurni
author_sort Lim, Yai-Fung
title Robust linear discriminant models to solve financial crisis in banking sectors
title_short Robust linear discriminant models to solve financial crisis in banking sectors
title_full Robust linear discriminant models to solve financial crisis in banking sectors
title_fullStr Robust linear discriminant models to solve financial crisis in banking sectors
title_full_unstemmed Robust linear discriminant models to solve financial crisis in banking sectors
title_sort robust linear discriminant models to solve financial crisis in banking sectors
publishDate 2014
url http://repo.uum.edu.my/16532/
http://doi.org/10.1063/1.4903673
_version_ 1644281994190782464
score 13.211869

Similar Items