Discarding Improper Values with Complete Case AnalysisΒΆ
This step deletes all data tuples containing improper values. It is widely used in many statistical packages.
Input Parameters
- Input data including improper values
- Definition of improper values (‘nan’, ‘inf’, or ‘null’, etc.)
Output Parameters
- Output data excluding improper values
Workflow
References
- G.E.A.P.A. Batista and M.C. Monard, An Analysis of Four Missing Data Treatment Methods for Supervised Learning, Applied Artificial Intelligence, vol. 17(5), pp. 519-533, 2003.
- S. Walfish, A review of statistical outlier methods. Pharmaceutical Technology, 2006. Retrieved from www.pharmtech.com.