Causal Mediation Analysis with Multi-dimensional and Indirectly Observed Mediators
This work addresses a limitation in causal inference for scientific applications like neuroscience, where mediators are often complex and unobserved, offering a method to improve mechanism analysis.
The paper tackles the problem of causal mediation analysis when mediators are multi-dimensional and indirectly observed, introducing a framework based on identifiable variational autoencoders that proves identifiability and demonstrates accurate effect estimation in synthetic experiments.
Causal mediation analysis (CMA) is a powerful method to dissect the total effect of a treatment into direct and mediated effects within the potential outcome framework. This is important in many scientific applications to identify the underlying mechanisms of a treatment effect. However, in many scientific applications the mediator is unobserved, but there may exist related measurements. For example, we may want to identify how changes in brain activity or structure mediate an antidepressant's effect on behavior, but we may only have access to electrophysiological or imaging brain measurements. To date, most CMA methods assume that the mediator is one-dimensional and observable, which oversimplifies such real-world scenarios. To overcome this limitation, we introduce a CMA framework that can handle complex and indirectly observed mediators based on the identifiable variational autoencoder (iVAE) architecture. We prove that the true joint distribution over observed and latent variables is identifiable with the proposed method. Additionally, our framework captures a disentangled representation of the indirectly observed mediator and yields accurate estimation of the direct and mediated effects in synthetic and semi-synthetic experiments, providing evidence of its potential utility in real-world applications.