Abstract

We summarize what we consider to be the two main limitations of the “Estimands for Recurrent Event Endpoints in the Presence of a Terminal Event” (Schmidli et al. Citation2022Schmidli, H., Roger, J. H., and Akacha, M. (2022), “Estimands for Recurrent Event Endpoints in the Presence of a Terminal Event,” Statistics in Biopharmaceutical Research, this issue. DOI: 10.1080/19466315.2021.1895883. [Taylor & Francis Online], [Google Scholar]). First, the authors did not give detailed guidance on how to choose an appropriate estimand in light of subject-matter considerations. Reasoning about the mechanism by which treatment affects different types of events is central when selecting a causal estimand, and such reasoning can be grounded in the interventionist mediation literature. Second, the article also did not discuss the crucial task of identification when the aim is to study a causal question. Thereby, the authors omit important differences in the uncertainty of the assumptions needed to target each estimand by particular statistical methods. These assumptions have crucial implications for the confidence that can be placed in a given effect estimate, and for the planning and collection of relevant variables in the study design.

摘要

我们总结了我们认为“存在终止事件时重复事件端点的估计值”的两个主要局限性（Schmidli 等人，引文2022 ）Schmidli, H.、Roger, JH和Akacha, M. ( 2022 )，“存在终端事件时重复事件终点的估计”，生物制药研究统计，本期。DOI：10.1080/19466315.2021.1895883。[泰勒和弗朗西斯在线] ，[谷歌学术] ）。首先，作者没有就如何根据主题考虑选择适当的估计值给出详细指导。在选择因果估计值时，推理治疗影响不同类型事件的机制是核心，这种推理可以以干预主义调解文献为基础。其次，文章也没有讨论当目的是研究因果问题时识别的关键任务。因此，作者忽略了通过特定统计方法针对每个估计值所需的假设不确定性的重要差异。这些假设对于给定效果估计的置信度以及研究设计中相关变量的规划和收集具有至关重要的影响。