Pennello Gene, Xu Dandan
Division of Imaging, Diagnostic and Software Reliability, Office of Science and Engineering Laboratories, Center for Devices and Radiological Health, U.S. Food and Drug Administration, Silver Spring, MD, USA.
Division of Biostatistics, Office of Clinical Evidence and Analysis, Office of Product Evaluation and Quality, Center for Devices and Radiological Health, U.S. Food and Drug Administration, Silver Spring, MD, USA.
Biom J. 2022 Feb;64(2):225-234. doi: 10.1002/bimj.202000320. Epub 2020 Dec 30.
In their paper, Liu et al. (2020) pointed out illogical discrepancies between subgroup and overall causal effects for some efficacy measures, in particular the odds and hazard ratios. As the authors show, the culprit is subgroups having prognostic effects within treatment arms. In response to their provocative findings, we found that the odds and hazard ratios are logic respecting when the subgroups are purely predictive, that is, the distribution of the potential outcome for the control treatment is homogeneous across subgroups. We also found that when we redefined the odds and hazards ratio causal estimands in terms of the joint distribution of the potential outcomes, the discrepancies are resolved under specific models in which the potential outcomes are conditionally independent. In response to other discussion points in the paper, we also provide remarks on association versus causation, confounding, statistical computing software, and dichotomania.
刘等人（2020年）在其论文中指出，对于某些疗效指标，特别是比值比和风险比，亚组效应与总体因果效应之间存在不合逻辑的差异。正如作者所示，罪魁祸首是在治疗组内具有预后效应的亚组。针对他们引人深思的发现，我们发现，当亚组纯粹具有预测性时，即对照治疗的潜在结果分布在各亚组间是同质的，比值比和风险比是符合逻辑的。我们还发现，当我们根据潜在结果的联合分布重新定义比值比和风险比因果估计量时，在潜在结果条件独立的特定模型下，差异会得到解决。针对该论文中的其他讨论点，我们还对关联与因果关系、混杂因素、统计计算软件和二分法癖发表了评论。
