The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON MATHEMATICS
Transactions ID Number: 31-293
Full Name: Zahayu Md Yusof
Position: Lecturer
Age: ON
Sex: Female
Address: 603, Jalan Atira 3, Taman Tunku Sarina, Bandar Darulaman, Jitra Kedah
Country: MALAYSIA
Tel:
Tel prefix:
Fax:
E-mail address: zahayu@uum.edu.my
Other E-mails: ayuyusof78@yahoo.com
Title of the Paper: Detecting Outliers by Using Trimming Criterion Based on Robust Scale Estimators with SAS Procedure
Authors as they appear in the Paper: Zahayu Md Yusof, Abdul Rahman Othman, Sharipah Soaad Syed Yahaya
Email addresses of all the authors: zahayu@uum.edu.my,oarahman@usm.my,sharipah@uum.edu.my
Number of paper pages: 10
Abstract: Non-normal data and heteroscedasticity are two common problems encountered when dealing with testing for location measures. Non-normality exists either from the shape of the distributions itself or by the presence of outliers. Outliers occur when the data values are very different from the data values for the majority of cases in the data set. Outliers are important because they can influence the results of the data analysis. This paper demonstrated the trimming criteria used in calculating the number of outliers in the data set by using robust scale estimators such as MADn, Tn and LMSn. This criterion will trim extreme values without priori determined trimming percentage. Discussion in detail about the trimming criterion and how extreme values are removed so as to minimize their influence on a data will be shown in this study by using sample data. We will present how these were done in a SAS program.
Keywords: Non-normality,Heteroscedasticity,Outliers,Trimming criteria,Trimming percentage,Robust scale estimator.
EXTENSION of the file: .pdf
Special (Invited) Session:
Organizer of the Session:
How Did you learn about congress:
IP ADDRESS: 124.13.1.172
