Comparing two tests used for diagnostic or screening purposes

被引：12

作者：

Geisser, S ^{[1
]}

机构：

[1] Univ Minnesota, Sch Stat, Minneapolis, MN 55455 USA

来源：

STATISTICS & PROBABILITY LETTERS | 1998年 / 40卷 / 02期

基金：

美国国家卫生研究院;

关键词：

Bayes; decision framework; diagnostic test; dichotomization; predictive value negative; predictive value positive; screening test;

D O I：

10.1016/S0167-7152(98)00067-4

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：

We present a Bayesian approach to the comparison of two binary diagnostic tests in a decision framework. We also show how a binary test that depends on a random variable may be optimally dichotomized with respect to the loss function. (C) 1998 Published by Elsevier Science B.V. All rights reserved.

引用

页码：113 / 119

页数：7

共 5 条

[1]

Gastwirth J.L., 1987, Stat. Sci., V2, P213

[2] OPTIMAL ADMINISTRATION OF DUAL SCREENING-TESTS FOR DETECTING A CHARACTERISTIC WITH SPECIAL REFERENCE TO LOW PREVALENCE DISEASES [J].