The bias of Fisher's linear discriminant function when the variancies are not equal

Terence J. O'Neill

doi:10.1016/0167-7152(92)90023-X

The bias of Fisher's linear discriminant function when the variancies are not equal

Terence J. O'Neill

Research output: Contribution to journal › Article › Research › peer-review

Abstract

Since Fisher's linear discriminant rule (FLDR) is the most widely used classification rule, its behaviour under non-standard situations is of great interest. This paper gives an expansion for the mean of FLDR when the equal variance matrices assumption is violated. The expansion has a particularly simple form for proportional covariance matrices. © 1992.

Original language	English
Pages (from-to)	205-210
Number of pages	6
Journal	Statistics and Probability Letters
Volume	14
Issue number	3
DOIs	https://doi.org/10.1016/0167-7152(92)90023-X
Publication status	Published - 24 Jun 1992
Externally published	Yes

Access to Document

10.1016/0167-7152(92)90023-X

Cite this

@article{1cf341994917418cb1b8fe7b769a91d3,

title = "The bias of Fisher's linear discriminant function when the variancies are not equal",

abstract = "Since Fisher's linear discriminant rule (FLDR) is the most widely used classification rule, its behaviour under non-standard situations is of great interest. This paper gives an expansion for the mean of FLDR when the equal variance matrices assumption is violated. The expansion has a particularly simple form for proportional covariance matrices. {\textcopyright} 1992.",

author = "O'Neill, \{Terence J.\}",

year = "1992",

month = jun,

day = "24",

doi = "10.1016/0167-7152(92)90023-X",

language = "English",

volume = "14",

pages = "205--210",

journal = "Statistics and Probability Letters",

issn = "0167-7152",

publisher = "CA: Journal of Cultural Analytics",

number = "3",

}

TY - JOUR

T1 - The bias of Fisher's linear discriminant function when the variancies are not equal

AU - O'Neill, Terence J.

PY - 1992/6/24

Y1 - 1992/6/24

N2 - Since Fisher's linear discriminant rule (FLDR) is the most widely used classification rule, its behaviour under non-standard situations is of great interest. This paper gives an expansion for the mean of FLDR when the equal variance matrices assumption is violated. The expansion has a particularly simple form for proportional covariance matrices. © 1992.

AB - Since Fisher's linear discriminant rule (FLDR) is the most widely used classification rule, its behaviour under non-standard situations is of great interest. This paper gives an expansion for the mean of FLDR when the equal variance matrices assumption is violated. The expansion has a particularly simple form for proportional covariance matrices. © 1992.

UR - https://www.scopus.com/pages/publications/38249012882

U2 - 10.1016/0167-7152(92)90023-X

DO - 10.1016/0167-7152(92)90023-X

M3 - Article

AN - SCOPUS:38249012882

SN - 0167-7152

VL - 14

SP - 205

EP - 210

JO - Statistics and Probability Letters

JF - Statistics and Probability Letters

IS - 3

ER -

The bias of Fisher's linear discriminant function when the variancies are not equal

Abstract

Access to Document

Other files and links

Fingerprint

Cite this