Sensitivity analysis for unobserved confounding of direct and indirect effects using uncertainty intervals

TL;DR

This paper introduces a sensitivity analysis method for mediation analysis with binary variables, accounting for unobserved confounding through correlation-based parameters and providing uncertainty intervals for direct and indirect effects.

Contribution

It proposes a novel parametric sensitivity analysis approach that incorporates multiple correlation parameters and accounts for sampling variability in mediation studies with binary data.

Findings

Method effectively assesses sensitivity to unobserved confounding.

Application demonstrates practical utility on Swedish Stroke Register data.

Provides uncertainty intervals for causal effect estimates.

Abstract

To estimate direct and indirect effects of an exposure on an outcome from observed data strong assumptions about unconfoundedness are required. Since these assumptions cannot be tested using the observed data, a mediation analysis should always be accompanied by a sensitivity analysis of the resulting estimates. In this article we propose a sensitivity analysis method for parametric estimation of direct and indirect effects when the exposure, mediator and outcome are all binary. The sensitivity parameters consist of the correlation between the error terms of the mediator and outcome models, the correlation between the error terms of the mediator model and the model for the exposure assignment mechanism, and the correlation between the error terms of the exposure assignment and outcome models. These correlations are incorporated into the estimation of the model parameters and identification sets are then obtained for the direct and indirect effects for a range of plausible correlation values. We take the sampling variability into account through the construction of uncertainty intervals. The proposed method is able to assess sensitivity to both mediator-outcome confounding and confounding involving the exposure. To illustrate the method we apply it to a mediation study based on data from the Swedish Stroke Register (Riksstroke).