Detection of different outlier scenarios in circular regression model using single-linkage method
Outliers are the set of data that are significantly deviates or dissimilar from the rest of the data set. In circular regression model, the existence of outliers are well known to give a large effect on the parameter estimates and inferences. In this study, we proposed clustering-based method using...
| Main Authors: | , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
IOP Publishing
2017
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/22307/ http://umpir.ump.edu.my/id/eprint/22307/ http://umpir.ump.edu.my/id/eprint/22307/1/Detection%20of%20different%20outlier%20scenarios.pdf |
| Summary: | Outliers are the set of data that are significantly deviates or dissimilar from the rest of the data set. In circular regression model, the existence of outliers are well known to give a large effect on the parameter estimates and inferences. In this study, we proposed clustering-based method using single linkage to detect multiple outliers. Single-linkage is one of several clustering methods, where the distance between two clusters is determined by a single pair element that are closest to each other. We examined two outlier scenarios with a certain degree of contamination. The performance of proposed method on different outlier scenarios are compared and the best method for each outlier scenario is chosen |
|---|