Journal of the Korean Statistical Society

The Korean Statistical Society (한국통계학회)
권호 표지

Generalization of Fisher′s linear discriminant analysis via the approach of sliced inverse regression

  • Published : 2001.06.01
Download PDF
⟨ Previous Next ⟩

Abstract

Despite of the rich literature in discriminant analysis, this complicated subject remains much to be explored. In this article, we study the theoretical foundation that supports Fisher's linear discriminant analysis (LDA) by setting up the classification problem under the dimension reduction framework as in Li(1991) for introducing sliced inverse regression(SIR). Through the connection between SIR and LDA, our theory helps identify sources of strength and weakness in using CRIMCOORDS(Gnanadesikan 1977) as a graphical tool for displaying group separation patterns. This connection also leads to several ways of generalizing LDA for better exploration and exploitation of nonlinear data patterns.

Keywords

References

  1. Classification and Regression Trees Breiman, L.;Friedman, J.;Olshen, R.;Stone, C.
  2. J. Amer. Stat. Assoc. v.86 Sliced Inverse Regression for Dimension Reduction Brillinger, D.R.;K.C. Li
  3. Academia Sinica, Ser A three-way subclassification approach to multiple-class discriminant analysis Chen, C.H.;Li, K.C.
  4. J. Amer. Stat. Assoc. v.89 On the Interpretation of Regression Plots Cook, R.D.
  5. J. Amer. Stat. Assoc. v.89 Reweighting to Achieve Elliptically Contoured Covariates in Regression Cook, R.D.;Nachtsheim, J.C.
  6. J. Amer. Stat. Assoc. v.86 Comments on Sliced Inverse Regression for Dimension Reduction Cook, R.D.;Weisberg, S.;K.C. Li
  7. Chinese Civilization : A Sourcebook(2nd ed.) Ebrey, P.
  8. Ann. Eugen. v.7 The Use of Multiple Measurements in Taxonomic Problems Fisher, R.A.
  9. Ann. Eugen. v.8 The Statistical Utilization of Multiple Measurements Fisher, R.A.
  10. IEEE Transactions on Computers v.26 A Recursive Partitioning Decision Rule for Nonparametric Classification Friedman, J.H.
  11. Introduction to Statistical Pattern Recognition Fukunaga;Keinosuke
  12. Neural Networks v.1 Analysis of hidden units in a layered network trained to classify sonar targets Gorman, R.P.;Sejnowski, T.J.
  13. Methods for statistical data analysis of multivariate observations Gnanadesikan, R.
  14. Ann, Stat. v.21 On Almost Linearity of Low Dimensional Projection from High Dimensional Data Hall, P.;Li, K.C.
  15. Ann, Stat. v.20 An Asymptotic Theory for Sliced Inverse Regression Hsing, T.;Carroll, R.J.
  16. IEEE Transactions on Computers v.21 A Nonparametric Valley-Seeking Technique for Cluster Analysis Koontz, W.;Fukunaga, K.
  17. IEEE Transactions on Computers v.25 A Graphic-Theoretic Approach to Nonparametric Cluster Analysis Koontz, W.;Narendra, P.;Fukunaga, K.
  18. J. Amer. Stat. Assoc. v.86 Sliced Inverse Regression for Dimension Reduction Li, K.C.
  19. Probability and Statistics Uncertainty Analysis for Mathematical Models with SIR Li, K.C.;Z.P. Jiang(ed.);S.H. Yan(ed.);P. Cheng(ed.);R. Wu(ed.)
  20. J. Amer. Stat. Assoc. v.87 On Principal Hessian Directions for Data Visualization and Dimension Reduction: Another Application of Stein's Lemma Li, K.C.
  21. J. Amer. Stat. Assoc. v.83 Tree-Structured Classification via Generalized Discriminant Analysis Loh, W.Y.;Vanichsetakul, N.
  22. Advanced Statistical Methods in Biometric Research Rao, C.R.
  23. J. Amer. Stat. Assoc. v.89 Determining the Dimensionality in Sliced Inverse Regression Schott, J.R.
  24. Technometrics v.18 On the Effects of Dimension in Discriminant Analysis Van Ness, J.W.;Simpson, C.
  25. Ann. Stat. v.24 Asymptotics for Kernel Estimate of Sliced Inverse Regression Zhu, L.X.;Fang, K.T.
  26. Statistica Sinica v.5 Asymptotics of Sliced Inverse Regression Zhu, L.X.;Ng