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...
| Main Authors: | , , , , , , , |
|---|---|
| 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 |