Journal of the Korean Statistical Society

The Korean Statistical Society (한국통계학회)
권호 표지

A Bayesian Diagnostic Measure and Stopping Rule for Detecting Influential Observations in Discriminant Analysis

  • Kim, Myung-Cheol (Department of Industrial Engineering, Samchok National University, Kwangwon-do, Korea, 245-711) ;
  • Kim, Hea-Jung (Department of Statistics, Dongguk University, Seoul, Korea, 100-715)
  • Published : 2000.09.01
Download PDF
⟨ Previous Next ⟩

Abstract

This paper suggests a new diagnostic measure and a stopping rule for detecting influential observations in multiple discriminant analysis (MDA). It is developed from a Bayesian point of view using a default Bayes factor obtained from the fractional Bayes factor methodology. The Bayes factor is taken as a discriminatory information in MDA. It is shown that the effect of an observation over the discriminatory information is fully explained by the diagnostic measure. Based on the measure, we suggest a stopping rule for detecting influential observations in a given training sample. As a tool for interpreting the measure a graphical method is sued. Performance of the method is used. Performance of the method is examined through two illustrative examples.

Keywords

References

  1. An Introduction to Multivariate Statistical Analysis Anderson, T.W.
  2. Journal of the Americal Statistical Association v.91 The intrinsic Bayes factor for model selection and prediction Berger, J.O.;Pericchi, L.
  3. Journal of the Americal Statistical Association v.82 Testing a point null hypothesis : The reconciliability of P-values and evidence Berger, J.O.;Sellke, T.
  4. Biometrika v.78 The influence of observations on misclassification probability estimates in linear discriminant analysis Critchley, F.;Vitiello, C.
  5. Optimal Statistical Decisions DeGroot, M.H.
  6. Statistics and Probability Letters v.13 Some diagnostic measures in discriminant analysis Fung, W.K.
  7. Journal of the Americal Statistical Association v.90 Diagnostics in linear discriminant analysis Fung, W.K.
  8. Statistician v.48 Outlier diagnostics in several multivariate samples Fung, W.K.
  9. Topics in Applied Multivatiate Analysis Hawkins, D.M.
  10. Appliced Discriminant Analysis Huberty, C.J.
  11. Theory of Probability Jeffreys, H.
  12. Journal of Business and Economic Statistics v.5 The detection of influential observations for allocation, separation, and the determination of probabilities in a Bayesian framework Johnson, W.
  13. Journal of the Americal Statistical Association v.90 Bayes factors Kass, R.E.;Raftery, A.E.
  14. Bayesian Statistics: An Introduction Lee, P.M.
  15. Postrior Probabilities of Alternative Linear Models Lempers, F.B.
  16. Discriminant Analysis and Statistical Pettern Recognition McLachlan, G.J.
  17. Journal of the Royal Statistical Society, B v.57 Fractional Bayes Factors for Model Comparisons O'Hagan, A.
  18. Biometrika v.77 Measuring the effect of observatios on Bayes factors Pettit, L.I.;Young, K.D.S.
  19. Methods of Multivatiate Analysis Rencher, A.C.
  20. Journal of the Americal Statistical Association v.85 Unmasking multivariate outliers and leverage points (with discussion) Rousseeuw, P.J.;Zomeren V.
  21. Journal of the Royal Statistical Society, B v.44 Bayes Factors for Linear and Log-linear Models with Vague Priot Information Spiegelhalter, D.J.;Smith, A.F.M.