SIMPLIFIED MAXIMUM LIKELIHOOD INFERENCE BASED ON THE LIKELIHOOD DECOMPOSITION FOR MISSING DATA

被引:0
|
作者
Jung, Sangah [1 ]
Park, Sangun [1 ]
机构
[1] Yonsei Univ, Dept Appl Stat, Seoul 120749, South Korea
基金
新加坡国家研究基金会;
关键词
Fisher information ratio; likelihood decomposition; non-monotone missing data; MULTIVARIATE NORMAL-DISTRIBUTION; INCOMPLETE-DATA; CONTINGENCY-TABLES; SAMPLE-SURVEYS; EM ALGORITHM; PARAMETERS; MODELS;
D O I
10.1111/anzs.12040
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 propose an estimation method when sample data are incomplete. We decompose the likelihood according to missing patterns and combine the estimators based on each likelihood weighting by the Fisher information ratio. This approach provides a simple way of estimating parameters, especially for non-monotone missing data. Numerical examples are presented to illustrate this method.
引用
收藏
页码:271 / 283
页数:13
相关论文
共 50 条