Platt Robert W, Schisterman Enrique F, Cole Stephen R
Department of Pediatrics and Epidemiology, McGillUniversity, Montreal, Quebec, Canada.
Am J Epidemiol. 2009 Sep 15;170(6):687-94. doi: 10.1093/aje/kwp175. Epub 2009 Aug 12.
According to the authors, time-modified confounding occurs when the causal relation between a time-fixed or time-varying confounder and the treatment or outcome changes over time. A key difference between previously described time-varying confounding and the proposed time-modified confounding is that, in the former, the values of the confounding variable change over time while, in the latter, the effects of the confounder change over time. Using marginal structural models, the authors propose an approach to account for time-modified confounding when the relation between the confounder and treatment is modified over time. An illustrative example and simulation show that, when time-modified confounding is present, a marginal structural model with inverse probability-of-treatment weights specified to account for time-modified confounding remains approximately unbiased with appropriate confidence limit coverage, while models that do not account for time-modified confounding are biased. Correct specification of the treatment model, including accounting for potential variation over time in confounding, is an important assumption of marginal structural models. When the effect of confounders on either the treatment or outcome changes over time, time-modified confounding should be considered.
据作者称，当固定时间或随时间变化的混杂因素与治疗或结局之间的因果关系随时间变化时，就会出现时间修正混杂。先前描述的随时间变化的混杂与提出的时间修正混杂之间的一个关键区别在于，在前者中，混杂变量的值随时间变化，而在后者中，混杂因素的效应随时间变化。作者使用边际结构模型，提出了一种在混杂因素与治疗之间的关系随时间修正时考虑时间修正混杂的方法。一个说明性示例和模拟表明，当存在时间修正混杂时，为考虑时间修正混杂而指定治疗权重的逆概率的边际结构模型在适当的置信区间覆盖下仍大致无偏，而未考虑时间修正混杂的模型则存在偏差。正确设定治疗模型，包括考虑混杂因素随时间的潜在变化，是边际结构模型的一个重要假设。当混杂因素对治疗或结局的效应随时间变化时，应考虑时间修正混杂。
