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

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.

[img] Text
P9886_5e0eb73aa1a584c2914199353b535edd.pdf
Restricted to Registered users only

Download (555kB) | Request a copy

Abstract

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.

Item Type: Conference or Workshop Item (Paper)
Subjects: Q Science > QA Mathematics > QA76 Computer software
Depositing User: Mr. Abdul Rahim Mat Radzuan
Date Deposited: 24 Apr 2022 00:36
Last Modified: 24 Apr 2022 00:36
URI: http://eprints.uthm.edu.my/id/eprint/6976

Actions (login required)

View Item View Item