Note on the Comparison of Some Outlier Labeling Techniques
Abstract
Problem statement: Methods proposed for estimating and resolving outliers are compared. Approach: In this respect, we exploit three well-known classifiers for identifying outliers to establish guidelines for the choice of outlier detection methods. Results: It was shown that the standard deviation is inappropriate to use here because it is highly sensitive to extreme values. Conclusion/Recommendations: The result of these estimated outliers is a better way of resolving large population.
DOI: https://doi.org/10.3844/jmssp.2011.353.355
Copyright: © 2011 N. P. Olewuezi. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
- 4,305 Views
- 4,300 Downloads
- 19 Citations
Download
Keywords
- Outlier detection
- detection methods
- extreme values
- Standard Deviation (SD)
- Median Absolute Deviation (MAD)
- breakdown point
- labeling methods