Classes of four-fold table quantifiers

  • Jan Rauch
Communications Session 8. Attribute Selection
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1510)

Abstract

Four-fold table logical calculi are defined. Formulae of these calculi correspond to patterns based on four-fold contingency tables of two Boolean attributes. An FFT quantifier is a part of the formula, it corresponds to an assertion concerning frequencies from four-fold table. Several classes of FFT quantifiers are defined and studied. It is shown that each particular class has interesting properties from the point of view of KDD. Deduction rules concerning formulae of four-fold tables calculi are demonstrated. It is shown that complex computation of statistical tests can be avoided by using tables of critical frequencies.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Aggraval, R. et al: Fast Discovery of Association Rules. In Fayyad, U. M. et al.: Advances in Knowledge Discovery and Data Mining. AAAI Press/The MIT Press, 1996, 307–328Google Scholar
  2. 2.
    Hájek, P., Havránek T.: Mechanising Hypothesis Formation—Mathematical Foundations for a General Theory. Berlin-Heidelberg-New York, Springer-Verlag, 1978, 396 p.Google Scholar
  3. 3.
    Hájek, P.—Havránek, T., Chytil M.: Metoda GUHA. Praha, Academia, 1983, 314 p. (in Czech)Google Scholar
  4. 4.
    Hájek, P., Sochorová, A., Zvárová, J.: GUHA for personal computers. Computational Statistics & Data Analysis 19, (1995) 149–153MATHCrossRefGoogle Scholar
  5. 5.
    Rauch, J.: Logical foundations of mechanizing hypotheses formation from databases (in Czech). Thesis, Mathematical Institute of Czechoslovak Academy of Sciences Prague, 1986, 133 p.Google Scholar
  6. 6.
    Rauch, J.: GUHA as a Data Mining Tool. In: Practical Aspects of Knowledge Management. Schweizer Informatiker Gesellshaft Basel, 1996Google Scholar
  7. 7.
    Rauch, J.: Logical Calculi for Knowledge Discovery in Databases. In Principles of Data Mining and Knowledge Discovery, (J. Komorowski and J. Zytkow, eds.), Springer Verlag, Berlin, 47–57, 1997.Google Scholar
  8. 8.
    Rauch, J.: Four-Fold Table Calculi. LISp, Technical Report LiSp9710 (in Czech), 1998Google Scholar
  9. 9.
    Zembowicz R.—Zytkow J.: From Contingency Tables to Various Forms of Knowledge in Databases. In Fayyad, U. M. et al.: Advances in Knowledge Discovery and Data Mining. AAAI Press/The MIT Press, 1996. s. 329–349.Google Scholar

Copyright information

© Springer-Verlag 1998

Authors and Affiliations

  • Jan Rauch
    • 1
  1. 1.Laboratory of Intelligent Systems, Faculty of Informatics and StatisticsUniversity of EconomicsPragueCzech Republic

Personalised recommendations