| Article ID | Journal | Published Year | Pages | File Type |
|---|---|---|---|---|
| 1154673 | Statistics & Probability Letters | 2006 | 8 Pages |
Abstract
Logistic discriminant analysis is frequently applied to data sets with discrete observed variables. When atypical observations exist in a data set, they may exert undue influence on the result of the analysis. The local influence approach is employed to develop diagnostic measures for identifying influential patterns in two-group logistic discriminant analysis. Examples based on real data are used for illustration.
Keywords
Related Topics
Physical Sciences and Engineering
Mathematics
Statistics and Probability
Authors
Wai-Yin Poon,