Clinical studies are often encountered with truncation-by-death issues, which render the outcomes undefined. Statistical analysis based only on observed survivors may lead to biased results because the characters of survivors may differ greatly between treatment groups. Under the principal stratification framework, a meaningful causal parameter, the survivor average causal effect, in the always-survivor group can be defined. This causal parameter may not be identifiable in observational studies where the treatment assignment and the survival or outcome process are confounded by unmeasured features. In this paper, we propose a new method to deal with unmeasured confounding when the outcome is truncated by death. First, a new method is proposed to identify the heterogeneous conditional survival average causal effect based on a substitutional variable under monotonicity. Second, under additional assumptions, the survivor average causal effect on the whole population is identified. Furthermore, we consider estimation and inference for the conditional survivor average causal effect based on parametric and nonparametric methods. The proposed method can be used for post marketing drug safety or efficiency by utilizing real world data.
翻译:临床研究往往遇到截断因死亡引起的问题,结果无法界定。仅根据观察到的幸存者进行的统计分析可能导致有偏差的结果,因为幸存者的个性在治疗群体之间可能差异很大。在主要分层框架下,可以确定一个有意义的因果参数,在总是幸存者群体中,幸存者的平均因果效果。这一因果参数在观察研究中可能无法识别,因为治疗任务以及生存或结果过程因非计量特征而混杂。在本文件中,我们提出了一种新的方法,在结果因死亡而被截断时,处理无法计量的混杂结果。首先,提出了一种新的方法,根据单一性下的替代变量,确定多种有条件生存条件平均因果效应。第二,根据其他假设,确定了幸存者对整个人口的平均因果影响。此外,我们考虑根据参数和非对数方法对有条件幸存者平均因果影响的估计和推断。拟议方法可用于销售后药品安全或利用真实世界数据提高效率。