DETECTION OF OUTLIERS AND INFLUENTIAL OBSERVATIONS IN REGRESSION-ANALYSIS USING STOCHASTIC PRIOR INFORMATION

被引:2
|
作者
TROSKIE, CG
CHALTON, DO
STEWART, TJ
JACOBS, M
机构
[1] UNIV CAPE TOWN,DEPT STAT SCI,RONDEBOSCH 7700,SOUTH AFRICA
[2] S AFRICAN MRC,INST BIOSTAT,TYGERBERG 7505,SOUTH AFRICA
关键词
OUTLIERS; INFLUENTIAL OBSERVATIONS; RIDGE; PRINCIPAL COMPONENTS; STOCHASTIC PRIOR INFORMATION;
D O I
10.1080/03610929408831457
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
When stochastic prior information is available there can be a considerable improvement in the estimation of beta in the usual model Y = X beta + e. Test statistics and diagnostics are developed to test for outliers and to detect influential observations when the residuals are analysed after these residuals have been computed using stochastic prior information. Applications to Ridge, Generalized Ridge and Stein type estimators and some examples are given.
引用
收藏
页码:3453 / 3476
页数:24
相关论文
共 50 条