ABDAN, AZLINA (2003) Perbandingan Antara Metodologi Analisa Penjelajahan Data (Exploratory Data Analysis) Dengan Metodologi Kelompok (Clustering Methodology) Dalam Pengenalpasttan Titik-Titik Terpencil. Other thesis, Universiti Teknologi Malaysia.
Download (2581Kb) | Preview
Identifying outlier is a fundamental stepi n the regression model building process. Outlying observation should be identified because of their potential effect on the fitted model.As a result of the need to identifu outliers,numerous outlying measures are built. Graph technique in exploratory data analysis is one graphical method to identify outlier for data.However these outlying measures work well when a regression data set contains only a single outlying point and it is well established that regression real data sets may have multiple outlying observations that individually are not easy identified by the same measures. Sebert et. al (1998) proposed clustering methodolory to identify multiple outlying observations bay utilizing the standardized predicted and residuals value from least square fit. Two techniques on classic data sets and research data set. S-Plus package will be used for this analysis.
|Item Type:||Thesis (Other)|
|Subjects:||Q Science > QA Mathematics > QA75 Electronic computers. Computer science|
|Divisions:||Faculty of Computer Science and Information System > Industrial Computing and Modelling|
|Depositing User:||Unnamed user with email firstname.lastname@example.org|
|Date Deposited:||04 Jul 2013 07:07|
|Last Modified:||04 Jul 2013 07:07|
Actions (login required)