Journal of the Korean Statistical Society

The Korean Statistical Society (한국통계학회)
권호 표지

Local Influence Assessment of the Misclassification Probability in Multiple Discriminant Analysis

  • Jung, Kang-Mo (Department of Computer Science and Statistics, Kunsan National University)
  • Published : 1998.12.01
Download PDF
⟨ Previous Next ⟩

Abstract

The influence of observations on the misclassification probability in multiple discriminant analysis under the equal covariance assumption is investigated by the local influence method. Under an appropriate perturbation we can get information about influential observations and outliers by studying the curvatures and the associated direction vectors of the perturbation-formed surface of the misclassification probability. We show that the influence function method gives essentially the same information as the direction vector of the maximum slope. An illustrative example is given for the effectiveness of the local influence method.

Keywords

References

  1. Applied Statistics v.27 The influence function as an aid in outlier detection in discriminant analysis Campbell, N. A.
  2. Journal of the Royal Statistical Society, Series B v.48 Assessment of local influence (with discussion) Cook, R. D.
  3. Biometrika v.78 The influence of observations on misclas-sification probability estimates in linear discriminant analysis Critchley, F.;Vitiello, C.
  4. Statistics & Probability Letters v.13 Some diagnostic measures in discriminant analysis Fung, W. -K.
  5. Communications in Statistics - Theory and Methods v.25 The influence of observations on misclassification prob-ability in multiple discriminant analysis Fung, W. -K.
  6. Applied multivariate statistical analysis, 3ed Johnson, R. A.;Wichern, D. W.
  7. Journal of the Japanese Society of Computational Statistics v.10 Second order local influ-ence in linear discriminant analysis Jung, K. -M.;Kim, M. G.;Kim, B. C.
  8. Journal of the Korean Society of Computational Statistics v.25 Local influence on misclassification probability Kim, M. G.
  9. Journal of the Royal Statistical Society, Series B v.55 Second-order approach to local influence Wu, X;Luo, Z