Department of Mathematics and Statistics, Georgia State University, Atlanta, GA, USA.
Stat Methods Med Res. 2020 Dec;29(12):3457-3491. doi: 10.1177/0962280220929042. Epub 2020 Jun 17.
In medical diagnostic studies, a diagnostic test can be evaluated based on its sensitivity under a desired specificity. Existing methods for inference on sensitivity include normal approximation-based approaches and empirical likelihood (EL)-based approaches. These methods generally have poor performance when the specificity is high, and some require choosing smoothing parameters. We propose a new influence function-based empirical likelihood method and Bayesian empirical likelihood methods to overcome such problems. Numerical studies are performed to compare the finite sample performance of the proposed approaches with existing methods. The proposed methods are shown to perform better in terms of both coverage probability and interval length. A real data set from Alzheimer's Disease Neuroimaging Initiative (ANDI) is analyzed.
在医学诊断研究中，可以根据所需的特异性来评估诊断测试的灵敏度。现有的灵敏度推断方法包括基于正态逼近的方法和基于经验似然 (EL) 的方法。当特异性较高时，这些方法的性能通常较差，并且有些方法需要选择平滑参数。我们提出了一种新的基于影响函数的经验似然方法和贝叶斯经验似然方法来克服这些问题。进行了数值研究以比较所提出的方法与现有方法的有限样本性能。结果表明，所提出的方法在覆盖概率和区间长度方面都表现更好。分析了来自阿尔茨海默病神经影像学倡议 (ANDI) 的真实数据集。
