A Note on NPML Estimation for Exponential Family Regression Models with Unspecified Dispersion Parameter

被引：0
|
作者：
Einbeck, Jochen [1 ]
Hinde, John [1 ]
机构：
[1] Natl Univ Ireland, Dept Math, Galway, Ireland
来源：
AUSTRIAN JOURNAL OF STATISTICS | 2006年 / 35卷 / 2-3期
基金：
爱尔兰科学基金会;
关键词：
EM Algorithm; Random Effect Models; Nonparametric Maximum Likelihood; Overdispersion; Gamma Distribution; Generalized Linear Model;
D O I：
暂无
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：
Nonparametric maximum likelihood (NPML) estimation for exponential families with unspecified dispersion parameter A suffers from computational instability, which can lead to highly fluctuating EM trajectories and suboptimal solutions, in particular when A is allowed to vary over mixture components. In this paper, a damped version of the EM algorithm is proposed to cope with these problems.
引用
收藏
页码：233 / 243
页数：11
相关论文
共 50 条
12345