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 |
| Summary: | 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. |
|---|