Construction of simultaneous confidence bands for a percentile hyper-plane with predictor variables constrained in an ellipsoidal region

被引：3

作者：

Zhou, Sanyu ^{[1
]}

Wang, Defa ^{[2
]}

Zhu, Jingjing ^{[1
]}

机构：

[1] Shanghai Univ Finance & Econ, Sch Urban & Reg Sci, Inst Finance & Econ Res, 777 Guoding Rd, Shanghai 200433, Peoples R China

[2] Shanghai Univ Finance & Econ, Sch Stat & Management, 777 Guoding Rd, Shanghai 200433, Peoples R China

来源：

STATISTICAL PAPERS | 2020年 / 61卷 / 03期

关键词：

Simultaneous inference; Average width criterion; Statistical simulation; Percentile hyper-plane; MULTIPLE LINEAR-REGRESSION; DOSE RISK-ESTIMATION; OPTIMAL DESIGNS; OPTIMALITY;

D O I：

10.1007/s00362-018-0990-4

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：

This paper provides the method of constructing the simultaneous confidence band for a percentile hyper-plane with predictor variables constrained in an ellipsoidal region. The band is compared with that on a rectangular region. It is shown that the band on the ellipsoidal region has a big advantage. The proposed method allows to construct the Type I band and the Type II band, and also allows to constrain the predictor variables either in finite intervals or in infinite intervals. In order to evaluate the efficiency of the band, the average width criterion is introduced, under which the Type I band and the Type II band are compared. All stated above are illustrated by a real example of a leaching rate study.

引用

页码：1335 / 1346

页数：12

共 25 条

[1] Confidence bands for low-dose risk estimation with quantal response data [J].