No label defined (Q3334802)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 3868441
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | No label defined |
scientific article; zbMATH DE number 3868441 |
Statements
1983
0 references
minimum error probability
0 references
discriminant analysis
0 references
pattern recognition
0 references
Mahalanobis distance
0 references
two-group classification
0 references
distributions of the eigenvalues
0 references
0.795985996723175
0 references
0.7876278162002563
0 references
0.7805009484291077
0 references
Statistics for the standard two-group classification problem may show a degradation of performance if the number p of features is increased. The paper is concerned with a sequence of such problems. The sample sizes are assumed to be of the same order of magnitude as p. The distributions of the eigenvalues of \(\Sigma\) and those of the corresponding contributions to Mahalanobis' \(\Delta^ 2\) (each contribution with probability \(p^{-1})\) are assumed to be convergent. The usual statistics, based on the inverse \(S^{-1}\) of the same covariance matrix, are generalized by considering \(\int(I+tS)^{- 1}da(t)\) instead of \(S^{-1}\). The results reported look interesting but the paper is very difficult to read.
0 references