Causal effect estimation from observational data is one of the essential problems in causal inference. However, most estimation methods rely on the strong assumption that all confounders are observed, which is impractical and untestable in the real world. We develop a mediation analysis framework inferring the latent confounder for debiasing both direct and indirect causal effects. Specifically, we introduce generalized structural equation modeling that incorporates structured latent factors to improve the goodness-of-fit of the model to observed data, and deconfound the mediators and outcome simultaneously. One major advantage of the proposed framework is that it utilizes the causal pathway structure from cause to outcome via multiple mediators to debias the causal effect without requiring external information on latent confounders. In addition, the proposed framework is flexible in terms of integrating powerful nonparametric prediction algorithms while retaining interpretable mediation effects. In theory, we establish the identification of both causal and mediation effects based on the proposed deconfounding method. Numerical experiments on both simulation settings and a normative aging study indicate that the proposed approach reduces the estimation bias of both causal and mediation effects.

翻译：从观测数据中估计因果效应是因果推断的核心问题之一。然而，大多数估计方法依赖于所有混杂变量均被观测到的强假设，这一假设在实际中难以成立且不可检验。我们提出了一种中介分析框架，通过推断潜在混杂因子来同时降低直接与间接因果效应的偏差。具体而言，我们引入了融合结构化潜在因子的广义结构方程模型，以提升模型对观测数据的拟合优度，并同时对中介变量和结果变量进行去混杂处理。该框架的主要优势在于，它利用从原因到结果经多重中介的因果路径结构来消除因果效应偏差，无需依赖潜在混杂因子的外部信息。此外，该框架具有灵活性，可整合强大的非参数预测算法，同时保留可解释的中介效应。理论上，我们基于所提出的去混杂方法建立了因果效应与中介效应的可识别性。在模拟实验及规范化老龄化研究上的数值实验表明，该方法能够降低因果效应与中介效应的估计偏差。