Abstract
Rough set based rule induction methods have been applied to knowledge discovery in databases, whose empirical results obtained show that they are very powerful and that some important knowledge has been extracted from datasets. However, quantitative evaluation of lower and upper approximation are based not on statistical evidence but on rather naive indices, such as conditional probabilities and functions of conditional probabilities. In this paper, we introduce a new approach to induced lower and upper approximation of original and variable precision rough set model for quantitative evaluation, which can be viewed as a statistical test for rough set methods. For this extension, chi-square distribution, F-test and likelihood ratio test play an important role in statistical evaluation. Chi-square test statistic measures statistical information about an information table and F-test statistic and likelihood ratio statistic are used to measure the difference between two tables.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Fisher, R.A. Statistical Methods for Research Workers (5th Ed.), Oliver&Boyd, Edinburgh, 1934.
Kryszkiewicz, M.and Rybinski, H. Incompleteness Aspects in Rough Set Approach. Proceedings of Sixth International Workshop on Rough Sets, Data Mining and Granular Computing, Duke, N.C., 1998.
Polkowski, L. and Skowron, A. (Eds.) Rough Sets and Knowledge Discovery 1 and 2, Physica Verlag, Heidelberg, 1998.
Pawlak, Z., Rough Sets. Kluwer Academic Publishers, Dordrecht, 1991.
Skowron, A. and Grzymala-Busse, J. From rough set theory to evidence theory. In: Yager, R., Fedrizzi, M. and Kacprzyk, J.(eds.) Advances in the Dempster-Shafer Theory of Evidence, pp. 193–236, John Wiley & Sons, New York, 1994.
Tsumoto, S. Knowledge discovery in clinical databases and evaluation of discovered knowledge in outpatient clinic. Information Sciences, 124, 125–137, 2000.
Tsumoto, S. Automated Discovery of Positive and Negative Knowledge in Clinical Databases based on Rough Set Model., IEEE EMB Magazine, 56–62, 2000.
Tsumoto, S. Statistical Extension of Rough Set Rule Induction Proceedings of SPIE: Data Mining and Knowledge Discovery: Theory, Tools, and Technology III, 2001.
Yao, Y.Y. and Wong, S.K.M., A decision theoretic framework for approximating concepts, International Journal of Man-machine Studies, 37, 793–809, 1992.
Yao, Y.Y. and Zhong, N., An analysis of quantitative measures associated with rules, N. Zhong and L. Zhou (Eds.), Methodologies for Knowledge Discovery and Data Mining, Proceedings of the Third Pacific-Asia Conference on Knowledge Discovery and Data Mining, LNAI 1574, Springer, Berlin, pp. 479–488, 1999.
Ziarko, W., Variable Precision Rough Set Model. Journal of Computer and System Sciences, 46, 39–59, 1993.
Zytkow, J. M. Granularity refined by knowledge: contingency tables and rough sets as tools of discovery Proceedings of SPIE: Data Mining and Knowledge Discovery: Theory, Tools and Technology II p. 82–91, 2000.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tsumoto, S. (2002). Statistical Test for Rough Set Approximation Based on Fisher’s Exact Test. In: Alpigini, J.J., Peters, J.F., Skowron, A., Zhong, N. (eds) Rough Sets and Current Trends in Computing. RSCTC 2002. Lecture Notes in Computer Science(), vol 2475. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45813-1_50
Download citation
DOI: https://doi.org/10.1007/3-540-45813-1_50
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-44274-5
Online ISBN: 978-3-540-45813-5
eBook Packages: Springer Book Archive