文章基本信息

标题：Modeling without a gold standard: stratification with stratum-dependent parameters
本地全文：下载
作者：Francisco Louzada ; Gilberto de Araujo Pereira ; Márcia M. Ferreira-Silva 等
期刊名称：RevStat : Statistical Journal
印刷版ISSN：1645-6726
出版年度：2014
卷号：12
期号：1
页码：85-99
出版社：Instituto Nacional de Estatística
摘要：Bayesian latent-class models have b een widely applied for assessing the performanceof diagnostic tests in the absence of a gold standard. We provide a short discussion onidentifiability issues appearing under the absence of a gold standard, and construct anextension of the well-known Hui–Walter stratification mo del which allows for stratum-dependent parameters. We illustrate our approach using a Chagas disease case studyon blood donors from Brazil
关键词：absence of a gold standard; diagnostic test; identifiability; sample size; stratification