Communications for Statistical Applications and Methods

The Korean Statistical Society (한국통계학회)
권호 표지

Tree-structured Classification based on Variable Splitting

  • Ahn, Sung-Jin (Department of Statistics, Gyeongsang National University)
  • Published : 1995.04.01
Download PDF
⟨ Previous Next ⟩

Abstract

This article introduces a unified method of choosing the most explanatory and significant multiway partitions for classification tree design and analysis. The method is derived on the impurity reduction (IR) measure of divergence, which is proposed to extend the proportional-reduction-in-error (PRE) measure in the decision-theory context. For the method derivation, the IR measure is analyzed to characterize its statistical properties which are used to consistently handle the subjects of feature formation, feature selection, and feature deletion required in the associated classification tree construction. A numerical example is considered to illustrate the proposed approach.

Keywords

References

  1. Biometrika v.63 no.1 Statistical diagnosis when basic cases are not classified with certainty Aitchison,J.;Begg,C.B.
  2. J. of Appl. Statist. v.18 A method of choosing multiway parititions for classification and decision trees Biggs, David;Ville, Barry de;Suen(ed.)
  3. Psychometrika v.52 no.3 Model selection and Akaike's information criterion (AIC): the general theory and its analytical extensions Bozdogan,H.
  4. Classification and regression trees Brieman,L.;Friedman,J.H.;Olsen,R.A.;Stone,C.G.
  5. IEEE Trans. on Pattern Anal. and Machine Intell. v.13 Optimal partitioning for classificaiton and regression trees Chou,P.A.
  6. An Introduction to Probability Theory and its Applications v.1 Feller, W.
  7. Algorithms for Clustering Data Jain,A.K.;Dubes,R.C.
  8. Appl. Statist. v.29 no.2 An exploratory technique for investigating large quantities of categorical data Kass,G.A.
  9. IEEE Trans. on Info. Theory v.37 no.1 Divergence measures based on the Shannon entropy Lin,J.
  10. Searching for Structure Sonquist,J.A.;Baker,E.;Morgan,J.
  11. Cluster Dissection and Analysis Spath,H.
  12. Psychometrika v.39 A comparative study of association measures Sarndal,C.E.
  13. IEEE Trans. on Pattern Anal. and Mach. Intell. v.13 A statistical-heuristic feature selection criterion for decision tree induction Zhou,X.J.;Dillon,T.S.