Peng F, Hall W J
Department of Mathematics and Statistics, University of Nebraska, Lincoln 68588-0323, USA.
Med Decis Making. 1996 Oct-Dec;16(4):404-11. doi: 10.1177/0272989X9601600411.
The authors introduce a Bayesian approach to generalized linear regression models for rating data observed in the evaluation of a diagnostic technology. Such models were previously studied using a non-Bayesian approach. In a Bayesian analysis, the difficulties inherent in an ordinal rating scale are circumvented by using data-augmentation techniques. Posterior distributions for the regression parameters- and thereby for receiver operating characteristic (ROC) curve parameters and values, for the area under a ROC curve, differences between areas, etc.-may then be computed by Markov-chain Monte Carlo methods. Inferences are made in standard Bayesian ways. The methods are exemplified by a study of ultrasonography rating data for the detection of hepatic metastases in patients with colon or breast cancer (previously analyzed) and the results compared.
作者介绍了一种贝叶斯方法，用于对诊断技术评估中观察到的评级数据的广义线性回归模型。此类模型此前是使用非贝叶斯方法进行研究的。在贝叶斯分析中，通过使用数据增强技术规避了有序评级量表固有的困难。然后可以通过马尔可夫链蒙特卡罗方法计算回归参数的后验分布，从而计算出受试者工作特征（ROC）曲线参数和值、ROC曲线下面积、面积之间的差异等。推断以标准贝叶斯方式进行。通过对结肠癌或乳腺癌患者肝转移检测的超声检查评级数据的研究（先前已分析）对这些方法进行了举例说明，并对结果进行了比较。
