UNIQUENESS OF PRINCIPAL POINTS FOR UNIVARIATE DISTRIBUTIONS

被引：26

作者：

LI, LN

FLURY, B

机构：

[1] NATL CTR ATMOSPHER RES,ADV STUDY PROGRAM,BOULDER,CO 80307

[2] INDIANA UNIV,DEPT MATH,BLOOMINGTON,IN 47405

来源：

STATISTICS & PROBABILITY LETTERS | 1995年 / 25卷 / 04期

关键词：

PRINCIPAL POINTS; K-MEANS ALGORITHM; NORMAL MIXTURE;

D O I：

10.1016/0167-7152(94)00237-3

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

This paper presents a proof of uniqueness of k principal of the univariate normal distributions. A sufficient condition of uniqueness is given, and a normal mixture example is discussed.

引用

页码：323 / 327

页数：5

共 14 条

[1]

Chow, On the uniqueness of best L<sub>2</sub>[0, 1] approximation by piecewise polynomials with variable breakpoints, Math. Comput., 30, pp. 571-585, (1982)

[2]

Cox, Note on grouping, Journal of the American Statistical Association, 52, pp. 543-547, (1957)

[3]

Day, Estimating the components of mixture of normal distributions, Biometrika, 56, pp. 463-474, (1969)

[4]

Dalenius, The problem of optimum stratification, Skandinavisk Aktuarietidskrift, 33, pp. 203-213, (1950)

[5]

Dalenius, Gurney, The problem of optimum stratification II, Skandinavisk Aktuarietidskrift, 34, pp. 203-213, (1951)

[6]

Eubank, Optimal grouping, spacing, stratification, and piecewise constant approximation, SIAM Rev., 30, pp. 404-420, (1988)

[7]

Flury, Principal points, Biometrika, 77, pp. 33-41, (1990)

[8]

Flury, Estimation of principal points, Applied Statistics, 42, (1993)

[9]

Hartigan, Clustering Algorithms, (1975)

[10]

Pearson, On linear and planes of closest fit to systems of points in space, Philosophical Magazine Series 6, 2, pp. 559-572, (1901)

← 1 2 →