From the Department of Sociology, University of Chicago, Chicago, IL.
Department of Sociology, Harvard University, Cambridge, MA.
Epidemiology. 2020 May;31(3):369-375. doi: 10.1097/EDE.0000000000001168.
Analyses of causal mediation are often complicated by treatment-induced confounders of the mediator-outcome relationship. In the presence of such confounders, the natural direct and indirect effects of treatment on the outcome, into which the total effect can be additively decomposed, are not identified. An alternative but similar set of effects, known as randomized intervention analogues to the natural direct effect (rNDE) and the natural indirect effect (rNIE), can still be identified in this situation, but existing estimators for these effects require a complicated weighting procedure that is difficult to use in practice. We introduce a new method for estimating the rNDE and rNIE that involves only a minor adaptation of the comparatively simple regression methods used to perform effect decomposition in the absence of treatment-induced confounding. It involves fitting (a) a generalized linear model for the conditional mean of the mediator given treatment and a set of baseline confounders and (b) a linear model for the conditional mean of the outcome given the treatment, mediator, baseline confounders, and a set of treatment-induced confounders that have been residualized with respect to the observed past. The rNDE and rNIE are simple functions of the parameters in these models when they are correctly specified and when there are no unobserved variables that confound the treatment-outcome, treatment-mediator, or mediator-outcome relationships. We illustrate the method by decomposing the effect of education on depression at midlife into components operating through income versus alternative factors. R and Stata packages are available for implementing the proposed method.
因果中介分析常常因中介-结局关系中的处理诱导混杂因素而变得复杂。在存在这种混杂因素的情况下，治疗对结局的总效应可加性分解的自然直接和间接效应无法确定。在这种情况下，仍然可以识别出一组替代但类似的效应，称为自然直接效应（rNDE）和自然间接效应（rNIE）的随机干预模拟，但这些效应的现有估计器需要复杂的加权程序，在实践中难以使用。我们引入了一种新的方法来估计 rNDE 和 rNIE，该方法仅涉及对相对简单的回归方法进行微小调整，这些回归方法用于在不存在处理诱导混杂的情况下进行效应分解。它涉及拟合 (a) 给定处理和一组基线混杂因素的中介条件均值的广义线性模型，以及 (b) 给定处理、中介、基线混杂因素和一组已残差化的与观察到的过去有关的处理诱导混杂因素的结局条件均值的线性模型。当这些模型正确指定且不存在混淆处理-结局、处理-中介或中介-结局关系的未观察变量时，rNDE 和 rNIE 是这些模型中参数的简单函数。我们通过将教育对中年期抑郁的影响分解为通过收入起作用的部分与其他因素来举例说明该方法。可用于实施所提出方法的 R 和 Stata 包。
