Some approximations to multivariate Polya-Eggenberger distributions with applications to hypothesis testing

被引：1

作者：

Childs, A ^{[1
]}

Balakrishnan, N ^{[1
]}

机构：

[1] McMaster Univ, Dept Math & Stat, Hamilton, ON L8S 4K1, Canada

来源：

COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION | 2002年 / 31卷 / 02期

关键词：

order statistics; multivariate Polya-Eggenberger distribution; Dirichlet distribution; multivariate normal distribution; multivariate hypergeometric distribution;

D O I：

10.1081/SAC-120003336

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：

In this paper, we will examine some approximations to multivariate Polya-Eggenberger distributions by continuous random variables. The continuous random variables will be chosen so as to have the same range of variation, means, variances and covariances as their discrete counterparts. We then show how these approximations can be used in testing hypotheses about the parameters of multivariate Polya-Eggenberger distributions.

引用

页码：213 / 243

页数：31

共 13 条

[1]

[Anonymous], BIOMETRIKA TABLES ST

[2]

Barnett V., 1984, Outliers in Statistical Data, V2nd

[3]

BARTLETT MS, 1946, J ROY STAT SOC B, V8, P128

[4] Some approximations to the multivariate hypergeometric distribution with applications to hypothesis testing [J].

Childs, A ;

Balakrishnan, N .

COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2000, 35 (02) :137-154

[5]

DAVID HA, 1981, ORDER STAT

[6]

Eisenhart C., 1947, SELECTED TECHNIQUES

[7]

Hawkins D.M, 1980, IDENTIFICATION OUTLI, V11, DOI [10.1007/978-94-015-3994-4, DOI 10.1007/978-94-015-3994-4]

[8]

Johnson N., 1994, CONTINUOUS UNIVARIAT, V1, DOI DOI 10.1016/0167-9473(96)90015-8

[9]

Johnson N.L., 1997, DISCRETE MULTIVARIAT

[10]

JOHNSON NL, 1960, BIOMETRIKA, V47, P463, DOI 10.1093/biomet/47.3-4.463

← 1 2 →