Standard Errors of Indices in Rough Set Data Analysis
The sample variation of indices for approximation of sets in the context of rough sets data analysis is considered. We consider the γ and α indices and some other ones – lower and upper bound approximation of decision classes. We derive confidence bounds for these indices as well as a two group comparison procedure. Finally we present procedures to compare the approximation quality of two sets within one sample.
KeywordsSimple Random Sampling Approximation Quality Decision Attribute Delta Method Rule System
Unable to display preview. Download preview PDF.
- 4.Agresti, A.: Categorical Data Analysis, 3rd edn. Wiley, New York (2012)Google Scholar
- 6.Research, I. W.: Mathematica Edition: Version 8.0. Wolfram Research, Inc., Champaign (2010)Google Scholar
- 8.Düntsch, I., Gediga, G.: Weighted λ precision models in rough set data analysis. In: Proceedings of the Federated Conference on Computer Science and Information Systems, Wrocław, Poland, pp. 309–316. IEEE (2012)Google Scholar