Pang, Yik Siong and Ahad, Nor Aishah and Syed Yahaya, Sharipah Soaad and Abdullah, Suhaida (2023) Robust Multiple Discriminant Rule Using Harrell-Davis\ Median Estimator: A Distribution-Free Approach to Cellwise-Casewise Outliers Coexistence. In: The 7th International Conference on Quantitative Sciences and its Applications (ICOQSIA2022), 22–24 August 2022, Sintok, Malaysia.

PDF - Published Version Restricted to Registered users only Download (383kB) | Request a copy

Abstract

Multivariate data may be contaminated by cellwise and or casewise outliers. Cellwise outliers are individual data points within a variable that are extreme whereas casewise outliers are observations that come from a different distribution. Similar to other parametric methods, the Classical Multiple Discriminant Rule (CMDR) achieve optimal performance only when the normality assumption is fulfilled. The coexistence of cellwise-casewise outliers can disrupt the data distribution of the sample. Thus, in order to alleviate the problem, this paper employed a distribution-free estimator, Harrell-Davis Median ,... together with Robust Covariance ... to construct Robust MDR (RMDRHD). The MDRs were evaluated based on misclassification rate via simulation study. The simulation results show that RMDR ... is able to achieve consistently lower misclassification rate than CMDR. Overall, the findings confirmed that the use of the distribution-free ... to robustify MDR is practical when dealing with both cellwise and casewise outliers

Item Type:	Conference or Workshop Item (Paper)
Additional Information:	Online ISSN 1551-7616 Print ISSN 0094-243X
Uncontrolled Keywords:	Cellwise Outliers, Casewise Outliers, Distribution-Free Estimator, Harrell-Davis Median Estimator
Subjects:	Q Science > QA Mathematics
Divisions:	School of Quantitative Sciences
Depositing User:	Mdm. Sarkina Mat Saad @ Shaari
Date Deposited:	15 Jul 2024 09:19
Last Modified:	15 Jul 2024 09:19
URI:	https://repo.uum.edu.my/id/eprint/31055

Actions (login required)

View Item