Non-asymptotic rate for high-dimensional covariance estimation with non-independent missing observations

被引:5
|
作者
Park, Seongoh [1 ]
Lim, Johan [1 ]
机构
[1] Seoul Natl Univ, Dept Stat, Seoul, South Korea
基金
新加坡国家研究基金会;
关键词
Convergence rate; Covariance matrix; Inverse probability weight estimator; Missing completely at random; MATRIX ESTIMATION;
D O I
10.1016/j.spl.2019.06.002
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 study non-asymptotic convergence rate of the inverse probability weight estimator of covariance matrix when some values of the data are missing completely at random. (C) 2019 Elsevier B.V. All rights reserved.
引用
收藏
页码:113 / 123
页数:11
相关论文
共 50 条