DOMAINS OF CONVERGENCE FOR THE EM ALGORITHM - A CAUTIONARY TALE IN A LOCATION ESTIMATION PROBLEM

被引：12

作者：

ARSLAN, O ^{[1
]}

CONSTABLE, PDL ^{[1
]}

KENT, JT ^{[1
]}

机构：

[1] UNIV LEEDS,DEPT STAT,LEEDS LS2 9JT,W YORKSHIRE,ENGLAND

来源：

STATISTICS AND COMPUTING | 1993年 / 3卷 / 03期

关键词：

ITERATIVE REWEIGHTING ALGORITHM; ROBUSTNESS; T-DISTRIBUTION; UPDATING FUNCTION;

D O I：

10.1007/BF00147772

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

The EM algorithm is a popular method for maximizing a likelihood in the presence of incomplete data. When the likelihood has multiple local maxima, the parameter space can be partitioned into domains of convergence, one for each local maximum. In this paper we investigate these domains for the location family generated by the t-distribution. We show that, perhaps somewhat surprisingly, these domains need not be connected sets. As an extreme case we give an example of a domain which consists of an infinite union of disjoint open intervals. Thus the convergence behaviour of the EM algorithm can be quite sensitive to the starting point.

引用

页码：103 / 108

页数：6

共 8 条

[1] FITTING OF POWER-SERIES, MEANING POLYNOMIALS, ILLUSTRATED ON BAND-SPECTROSCOPIC DATA [J].

BEATON, AE ;

TUKEY, JW .

TECHNOMETRICS, 1974, 16 (02) :147-185

[2] MAXIMUM LIKELIHOOD FROM INCOMPLETE DATA VIA EM ALGORITHM [J].

DEMPSTER, AP ;

LAIRD, NM ;

RUBIN, DB .

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-METHODOLOGICAL, 1977, 39 (01) :1-38

[3]

HAMPEL FR, 1986, ROBUST STATISTICS AP

[4]

Huber PJ., 1981, ROBUST STATISTICS

[5] ROBUST STATISTICAL MODELING USING THE T-DISTRIBUTION [J].

LANGE, KL ;

LITTLE, RJA ;

TAYLOR, JMG .

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1989, 84 (408) :881-896

[6]

LITTLE R, 1987, STATISTICAL ANAL MIS

[7] ON THE CONVERGENCE PROPERTIES OF THE EM ALGORITHM [J].

WU, CFJ .

ANNALS OF STATISTICS, 1983, 11 (01) :95-103

[8]

[No title captured]

← 1 →