In clinical trials, the efficacy of treatment might be dependent on the value of a covariate variable. Therefore, it might be possible to detect the region over the covariate variable where the two treatments under investigation do not have significantly different efficacy or the region of superiority of one treatment. The non-significant region can be verified to be a confidence interval for the abscissa of the intersection point of two regression lines, and each of the complementary regions of the confidence interval corresponds to a region of superiority. In this study, we develop a method of constructing the confidence interval based on the concept of a generalized pivotal quantity, so as to perform the task of detecting the possible three regions for a clinical trial. Two real-world examples are given to illustrate the application of our proposed method, and a simulation study is conducted to evaluate its performance.

在临床试验中，治疗效果可能取决于协变量的值。因此，有可能检测协变量变量的区域，其中所研究的两种治疗方法没有显着不同的疗效或一种治疗方法的优势区域。可以验证非显着区域为两条回归线交点横坐标的置信区间，置信区间的每个互补区域对应一个优势区域。在这项研究中，我们开发了一种基于广义关键量概念构建置信区间的方法，以执行检测临床试验可能的三个区域的任务。