UNIQUENESS OF THE MAXIMUM LIKELIHOOD ESTIMATOR FOR k-MONOTONE DENSITIES

被引：10

作者：

Seregin, Arseni ^{[1
]}

机构：

[1] Univ Washington, Dept Stat, Seattle, WA 98195 USA

来源：

PROCEEDINGS OF THE AMERICAN MATHEMATICAL SOCIETY | 2010年 / 138卷 / 12期

基金：

美国国家科学基金会;

关键词：

Uniqueness; k-monotone density; mixture models; density estimation; maximum likelihood; nonparametric estimation; shape constraints; MIXTURE LIKELIHOODS; GEOMETRY;

D O I：

10.1090/S0002-9939-2010-10496-3

中图分类号：

O29 [应用数学];

学科分类号：

070104 ;

摘要：

We prove uniqueness of the maximum likelihood estimator for the class of k-monotone densities.

引用

页码：4511 / 4515

页数：5

共 11 条

[1]

[Anonymous], 1970, CONVEX ANAL

[2]

BALABDAOUI F, 2004, THESIS U WASHINGTON

[3] Estimation of a k-monotone density: Limit distribution theory and the spline connection [J].

Balabdaoui, Fadoua ;

Wellner, Jon A. .

ANNALS OF STATISTICS, 2007, 35 (06) :2536-2564

[4] Estimation of a k-monotone density: characterizations, consistency and minimax lower bounds [J].

Balabdaoui, Fadoua ;

Wellner, Jon A. .

STATISTICA NEERLANDICA, 2010, 64 (01) :45-70

[5]

Groeneboom P, 2001, ANN STAT, V29, P1653

[6] MIXTURES OF EXPONENTIAL-DISTRIBUTIONS [J].

JEWELL, NP .

ANNALS OF STATISTICS, 1982, 10 (02) :479-484

[7] THE GEOMETRY OF MIXTURE LIKELIHOODS .2. THE EXPONENTIAL FAMILY [J].

LINDSAY, BG .

ANNALS OF STATISTICS, 1983, 11 (03) :783-792

[8] UNIQUENESS OF ESTIMATION AND IDENTIFIABILITY IN MIXTURE-MODELS [J].

LINDSAY, BG ;

ROEDER, K .

CANADIAN JOURNAL OF STATISTICS-REVUE CANADIENNE DE STATISTIQUE, 1993, 21 (02) :139-147

[9] THE GEOMETRY OF MIXTURE LIKELIHOODS - A GENERAL-THEORY [J].

LINDSAY, BG .

ANNALS OF STATISTICS, 1983, 11 (01) :86-94

[10]

LINDSAY BG, 1995, CBMS REGIONAL C SERI, V5

← 1 2 →