On sufficient conditions for the strong consistency of least-squares estimates

被引：0
|
作者：
da Silva, Joao Lita [1 ,2 ]
机构：
[1] Univ Nova Lisboa, Fac Sci & Technol, Dept Math, P-2829516 Quinta Da Torre, Caparica, Portugal
[2] Univ Nova Lisboa, Fac Sci & Technol, CMA, P-2829516 Quinta Da Torre, Caparica, Portugal
来源：
STATISTICS | 2014年 / 48卷 / 03期
关键词：
strong consistency; regression models; least-squares estimates; 60F15; REGRESSION-MODELS;
D O I：
10.1080/02331888.2012.760096
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：
The strong consistency of the least-squares estimates in regression models is obtained when the errors are i.i.d. with absolute moment of order r, 0 < r <= 2. The assumptions presented for the random error sequence will permit us to obtain improvements of the conditions on the regressors in order to obtain the strong consistency of the least-squares estimates in linear and nonlinear regression models.
引用
收藏
页码：657 / 667
页数：11
相关论文
共 50 条
12345