Non-linear Mediation Analysis with High-dimensional Mediators whose Causal Structure is Unknown

01/20/2020
by   Wen Wei Loh, et al.
0

With multiple potential mediators on the causal pathway from a treatment to an outcome, we consider the problem of decomposing the effects along multiple possible causal path(s) through each distinct mediator. Under Pearl's path-specific effects framework (Pearl, 2001; Avin et al., 2005), such fine-grained decompositions necessitate stringent assumptions, such as correctly specifying the causal structure among the mediators, and there being no unobserved confounding among the mediators. In contrast, interventional direct and indirect effects for multiple mediators (Vansteelandt and Daniel, 2017) can be identified under much weaker conditions, while providing scientifically relevant causal interpretations. Nonetheless, current estimation approaches require (correctly) specifying a model for the joint mediator distribution, which can be difficult when there is a high-dimensional set of possibly continuous and non-continuous mediators. In this article, we avoid the need for modeling this distribution, by building on a definition of interventional effects previously suggested by VanderWeele and Tchetgen Tchetgen (2017) for longitudinal mediation. We propose a novel estimation procedure that uses non-parametric estimates of the marginal (counterfactual) mediator distributions. The procedure is illustrated using publicly-available genomic data exploring the prognostic effect of microRNA miR-223 expression on the three-month mortality of patients suffering from an aggressive form of brain cancer, that is potentially mediated by expression values of multiple genes (Huang and Pan, 2016).

READ FULL TEXT
research
07/19/2019

Interventional Effect Models for Multiple Mediators

In settings that involve multiple mediators, approaches focusing on fine...
research
05/16/2022

Causal influence, causal effects, and path analysis in the presence of intermediate confounding

Recent approaches to causal inference have focused on the identification...
research
10/15/2022

Heterogeneous interventional indirect effects with multiple mediators: non-parametric and semi-parametric approaches

We propose semi- and non-parametric methods to estimate conditional inte...
research
04/03/2023

The synthetic instrument: From sparse association to sparse causation

In many observational studies, researchers are often interested in study...
research
09/21/2018

Causal mediation analysis in presence of multiple mediators uncausally related

Mediation analysis aims at disentangling the effects of a treatment on a...
research
05/19/2021

Multiply Robust Causal Mediation Analysis with Continuous Treatments

In many applications, researchers are interested in the direct and indir...
research
11/06/2021

Causal Mediation and Sensitivity Analysis for Mixed-Scale Data

The goal of causal mediation analysis, often described within the potent...

Please sign up or login with your details

Forgot password? Click here to reset