EPMC estimation in discriminant analysis when the dimension and sample sizes are large

被引：3

作者：

Tonda, Tetsuji ^{[1
]}

Nakagawa, Tomoyuki ^{[2
]}

Wakaki, Hirofumi ^{[2
]}

机构：

[1] Prefectural Univ Hiroshima, Fac Management & Informat Syst, Hiroshima 7348558, Japan

[2] Hiroshima Univ, Grad Sch Sci, Dept Math, Higashihiroshima 7398526, Japan

来源：

HIROSHIMA MATHEMATICAL JOURNAL | 2017年 / 47卷 / 01期

关键词：

Discriminant analysis; Classification; High dimensional; Asymptotic expansion; Expected probability of misclassification;

D O I：

10.32917/hmj/1492048847

中图分类号：

O1 [数学];

学科分类号：

0701 ; 070101 ;

摘要：

In this paper we obtain a higher order asymptotic unbiased estimator for the expected probability of misclassification (EPMC) of the linear discriminant function when both the dimension and the sample size are large. Moreover, we evaluate the mean squared error of our estimator. We also present a numerical comparison between the performance of our estimator and that of the other estimators based on Okamoto (1963, 1968) and Fujikoshi and Seo (1998). It is shown that the bias and the mean squared error of our estimator are less than those of the other estimators.

引用

页码：43 / 62

页数：20

共 50 条

[1] Asymptotic properties of the EPMC for modified linear discriminant analysis when sample size and dimension are both large
Hyodo, Masashi
Yamada, Takayuki
[J]. JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 2010, 140 (09) : 2739 - 2748
[2] Asymptotic results in canonical discriminant analysis when the dimension is large compared to the sample size
Fujikoshi, Yasunori
Himeno, Tetsuto
Wakaki, Hirofumi
[J]. JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 2008, 138 (11) : 3457 - 3466
[3] Interval estimation in discriminant analysis for large dimension
Yamada, Takayuki
Himeno, Tetsuto
Sakurai, Tetsuro
[J]. COMMUNICATIONS IN STATISTICS-THEORY AND METHODS, 2017, 46 (18) : 9042 - 9052
[4] A test for the equality of covariance matrices when the dimension is large relative to the sample sizes
Schott, James R.
[J]. COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2007, 51 (12) : 6535 - 6542
[5] Estimating the probabilities of misclassification using CV when the dimension and the sample sizes are large
Nakagawa, Tomoyuki
[J]. HIROSHIMA MATHEMATICAL JOURNAL, 2018, 48 (03) : 373 - 411
[6] Error bounds for asymptotic approximations of the linear discriminant function when the sample sizes and dimensionality are large
Fujikoshi, Y
[J]. JOURNAL OF MULTIVARIATE ANALYSIS, 2000, 73 (01) : 1 - 17
[7] DISCRIMINANT-ANALYSIS WHEN THE SAMPLE IS FINITE AND THE FEATURE SPACE DIMENSION INCREASES
SEMIVSKII, SV
[J]. THEORY OF PROBABILITY AND ITS APPLICATIONS, 1988, 32 (03) : 521 - 525
[8] DISCRIMINANT FUNCTIONS WHEN COVARIANCES ARE UNEQUAL AND SAMPLE SIZES ARE MODERATE
WAHL, PW
KRONMAL, RA
[J]. BIOMETRICS, 1977, 33 (03) : 479 - 484
[9] Interval estimation in two-group discriminant analysis under heteroscedasticity for large dimension
Yamada, Takayuki
[J]. COMMUNICATIONS IN STATISTICS-THEORY AND METHODS, 2018, 47 (23) : 5717 - 5728
[10] Asymptotic expansion and estimation of EPMC for linear classification rules in high dimension
Kubokawa, Tatsuya
Hyodo, Masashi
Srivastava, Muni S.
[J]. JOURNAL OF MULTIVARIATE ANALYSIS, 2013, 115 : 496 - 515

← 1 2 3 4 5 →