Discriminant Analysis with Icomplete Pattern Vectors

  • Hie Choon Chung (Department of Industrial Information Engineering, Kwangju University, Kwangju, 502-703, Korea)
  • Published : 1997.04.01

Abstract

We consider the problem of classifying a p x 1 observation into one of two multivariate normal populations when the training smaples contain a block of missing observation. A new classification procedure is proposed which is a linear combination of two discriminant functions, one based on the complete samples and the other on the incomplete samples. The new discriminant function is easy to use.

Keywords

References

  1. Psychometrika v.16 Classification by multivariate analysis Anderson, T. W.
  2. Journal of the American Statistical Association v.52 Maximum likelihood estimates for a multivariate normal distribution when some observations are missing Anderson, T. W.
  3. ASA Proceedings of Social Statistics Section Bohannon, Tom R.;Smith, W. B.
  4. Royal Statistical Society v.Algorithm AS214 Calculation of Monte Carlo confidence intervals Buckland, Stephen T.
  5. Journal of the American Statistical Association v.67 The treatment of missing values in discriminant analysis-1, The sampling experiment Chan, L. S.;Dunn, O. J.
  6. Journal of the American Statistical Association v.69 A note on the asymptotical aspect of the treatment of missing values in discriminant analysis Chan, L. S.;Dunn, O. J.
  7. Journal of Mathematical Analysis and Application v.171 An interval estimation of the probability of misclassification Dorvlo, Atsu S.S.
  8. CBMS-NSF Regional Conference Series in Applied Mathematics, 38. Society for Industrial and Applied Mathematics (SIAM) v.38 The jackknife, the bootstrap, and other resampling plans Efron, B.
  9. Journal of the American Statistical Association v.63 Estimation of parameters in the mutivariate normal distribution with missing observation Hocking, R. R.;Smith, W. B.
  10. Journal of Statistical Computation and Simulation v.11 The efficiency of Efron's bootstrap approach applied to error rate estimation in discriminant analysis McLachlan, G. J.
  11. Communications in Statistics-Theory and Methods v.21 Comparison of algorithm for replacing missing data in discriminant analysis Twedt, Daniel J.;Gill, D. S.