Identification of causal direct-indirect effects without untestable assumptions

TL;DR

This paper introduces a new causal effect measure in mediation analysis that is identifiable without untestable assumptions, allowing for accurate causal inference even when potential outcomes and mediators are dependent.

Contribution

It defines a novel causal direct and indirect effect that does not rely on the traditional untestable independence assumptions, expanding the scope of identifiable causal effects.

Findings

The new measure is identifiable from observed data despite dependence between potential outcomes and mediators.

Existing natural direct and indirect effects may be misleading when untestable assumptions are violated.

The proposed approach avoids pseudo-effects caused by assumption violations.

Abstract

In causal mediation analysis, identification of existing causal direct or indirect effects requires untestable assumptions in which potential outcomes and potential mediators are independent. This paper defines a new causal direct and indirect effect that does not require the untestable assumptions. We show that the proposed measure is identifiable from the observed data, even if potential outcomes and potential mediators are dependent, while the existing natural direct or indirect effects may find a pseudo-indirect effect when the untestable assumptions are violated.