本文提出了一种强大的方法来比较两个样本。所提出的方法通过从ROC曲线模型参数中得出推断来处理数据的比较。该方法根据经验敏感性和特异性从线性模型框架估计参数。然后使用一致的ROC参数在几种情况下给出比现有方法更强大的测试。此外,我们给出了一个基于柯西组合的综合统计数据,它在本文考虑的所有场景中都能很好地工作。我们还提供了一个有效的单层野生置换程序来计算统计量的P值。当潜在的连续生物标志物结果为非正常时,该方法特别有用。我们在新生儿听力学诊断示例中说明了所提出的方法。
This article proposes a powerful method to compare two samples. The proposed method handles comparison of data by drawing inference from ROC curve model parameters. The method estimates parameters from a linear model framework on the empirical sensitivities and specificities. The consistent ROC parameters are then used to give a more powerful test than existing methods in several situations. In addition, we present a comprehensive statistic based on the Cauchy combination, which works well in all scenarios considered in this article. We also offer an efficient one-layer wild permutation procedure to calculate the P-value of our statistic. The method is particularly useful when the underlying continuous biomarker results are non-normal. We illustrate the proposed methods in a neonatal audiology diagnostic example.