Comparison of Poisson mixture models for count data clusterization

被引：0

作者：

Susinskas, J ^{[1
]}

Radavicius, M ^{[1
]}

机构：

[1] Inst Math & Informat, LT-2600 Vilnius, Lithuania

来源：

INFORMATICA | 2002年 / 13卷 / 02期

关键词：

count data; clusterization; nonparametric Poisson mixtures; plug-in Bayes classification rule; maximum likelihood estimator; classification error rate;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Five methods for count data clusterization based on Poisson mixture models are described. Two of them are parametric, the others are semi-parametric. The methods emlploy the plug-in Bayes classification rule. Their performance is investigated by making use of computer simulation and compared mainly by the clusterization error rate. We also apply the clusterization procedures to real count data and discuss the results.

引用

页码：209 / 226

页数：18

共 8 条

[1]

Aivazyan S. A., 1989, Applied Statistics. Classification and Dimensionality Reduction

[2] A REVIEW OF RELIABLE MAXIMUM-LIKELIHOOD ALGORITHMS FOR SEMIPARAMETRIC MIXTURE-MODELS [J].

BOHNING, D .

JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 1995, 47 (1-2) :5-28

[3]

Everitt B. S., 1981, FINITE MIXTURE DISTR

[4]

Ibragimov IA, 1981, STAT ESTIMATION ASYM

[5] A REVIEW OF SEMIPARAMETRIC MIXTURE-MODELS [J].

LINDSAY, BG ;

LESPERANCE, ML .

JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 1995, 47 (1-2) :29-39

[6]

MCLACKLAN GJ, 1988, MIXTURE MODELS INFER

[7]

RADAVICIUS M, 1998, P 5 INT C COMP DAT A, V2, P49

[8] MIXTURE-MODELS FOR THE ANALYSIS OF REPEATED COUNT DATA [J].

VANDUIJN, MAJ ;

BOCKENHOLT, U .

APPLIED STATISTICS-JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES C, 1995, 44 (04) :473-485

← 1 →