An application of robust method in multiple linear regression model toward credit card debt

Credit card is a convenient alternative replaced cash or cheque, and it is essential component for electronic and internet commerce. In this study, the researchers attempt to determine the relationship and significance variables between credit card debt and demographic variables such as age, h...

Full description

Bibliographic Details
Main Authors: Azmi, Nur Amira, Rusiman, Mohd Saifullah, Khalid, Kamil, Roslan, Rozaini, Sufahani, Suliadi Firdaus, Mohamad, Mahathir, Mohd Salleh, Rohayu, Amir Hamzah, Nur Shamsidah
Format: Conference or Workshop Item
Language:English
Published: 2018
Subjects:
Online Access:http://eprints.uthm.edu.my/6976/
http://eprints.uthm.edu.my/6976/1/P9886_5e0eb73aa1a584c2914199353b535edd.pdf
_version_ 1848888965974720512
author Azmi, Nur Amira
Rusiman, Mohd Saifullah
Khalid, Kamil
Roslan, Rozaini
Sufahani, Suliadi Firdaus
Mohamad, Mahathir
Mohd Salleh, Rohayu
Amir Hamzah, Nur Shamsidah
author_facet Azmi, Nur Amira
Rusiman, Mohd Saifullah
Khalid, Kamil
Roslan, Rozaini
Sufahani, Suliadi Firdaus
Mohamad, Mahathir
Mohd Salleh, Rohayu
Amir Hamzah, Nur Shamsidah
author_sort Azmi, Nur Amira
building UTHM Institutional Repository
collection Online Access
description Credit card is a convenient alternative replaced cash or cheque, and it is essential component for electronic and internet commerce. In this study, the researchers attempt to determine the relationship and significance variables between credit card debt and demographic variables such as age, household income, education level, years with current employer, years at current address, debt to income ratio and other debt. The provided data covers 850 customers information. There are three methods that applied to the credit card debt data which are multiple linear regression (MLR) models, MLR models with least quartile difference (LQD) method and MLR models with mean absolute deviation method. After comparing among three methods, it is found that MLR model with LQD method became the best model with the lowest value of mean square error (MSE). According to the final model, it shows that the years with current employer, years at current address, household income in thousands and debt to income ratio are positively associated with the amount of credit debt. Meanwhile variables for age, level of education and other debt are negatively associated with amount of credit debt. This study may serve as a reference for the bank company by using robust methods, so that they could better understand their options and choice that is best aligned with their goals for inference regarding to the credit card debt.
first_indexed 2025-11-15T20:18:40Z
format Conference or Workshop Item
id uthm-6976
institution Universiti Tun Hussein Onn Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T20:18:40Z
publishDate 2018
recordtype eprints
repository_type Digital Repository
spelling uthm-69762022-04-24T00:36:49Z http://eprints.uthm.edu.my/6976/ An application of robust method in multiple linear regression model toward credit card debt Azmi, Nur Amira Rusiman, Mohd Saifullah Khalid, Kamil Roslan, Rozaini Sufahani, Suliadi Firdaus Mohamad, Mahathir Mohd Salleh, Rohayu Amir Hamzah, Nur Shamsidah QA76 Computer software Credit card is a convenient alternative replaced cash or cheque, and it is essential component for electronic and internet commerce. In this study, the researchers attempt to determine the relationship and significance variables between credit card debt and demographic variables such as age, household income, education level, years with current employer, years at current address, debt to income ratio and other debt. The provided data covers 850 customers information. There are three methods that applied to the credit card debt data which are multiple linear regression (MLR) models, MLR models with least quartile difference (LQD) method and MLR models with mean absolute deviation method. After comparing among three methods, it is found that MLR model with LQD method became the best model with the lowest value of mean square error (MSE). According to the final model, it shows that the years with current employer, years at current address, household income in thousands and debt to income ratio are positively associated with the amount of credit debt. Meanwhile variables for age, level of education and other debt are negatively associated with amount of credit debt. This study may serve as a reference for the bank company by using robust methods, so that they could better understand their options and choice that is best aligned with their goals for inference regarding to the credit card debt. 2018 Conference or Workshop Item PeerReviewed text en http://eprints.uthm.edu.my/6976/1/P9886_5e0eb73aa1a584c2914199353b535edd.pdf Azmi, Nur Amira and Rusiman, Mohd Saifullah and Khalid, Kamil and Roslan, Rozaini and Sufahani, Suliadi Firdaus and Mohamad, Mahathir and Mohd Salleh, Rohayu and Amir Hamzah, Nur Shamsidah (2018) An application of robust method in multiple linear regression model toward credit card debt. In: ISMAP 2017, October 28, 2017, Batu Pahat, Johor. https://doi.org/10.1088/1742-6596/995/1/012011
spellingShingle QA76 Computer software
Azmi, Nur Amira
Rusiman, Mohd Saifullah
Khalid, Kamil
Roslan, Rozaini
Sufahani, Suliadi Firdaus
Mohamad, Mahathir
Mohd Salleh, Rohayu
Amir Hamzah, Nur Shamsidah
An application of robust method in multiple linear regression model toward credit card debt
title An application of robust method in multiple linear regression model toward credit card debt
title_full An application of robust method in multiple linear regression model toward credit card debt
title_fullStr An application of robust method in multiple linear regression model toward credit card debt
title_full_unstemmed An application of robust method in multiple linear regression model toward credit card debt
title_short An application of robust method in multiple linear regression model toward credit card debt
title_sort application of robust method in multiple linear regression model toward credit card debt
topic QA76 Computer software
url http://eprints.uthm.edu.my/6976/
http://eprints.uthm.edu.my/6976/
http://eprints.uthm.edu.my/6976/1/P9886_5e0eb73aa1a584c2914199353b535edd.pdf