# Identifying mediating variables with graphical models: an application to the study of causal pathways in people living with HIV

## TL;DR

This paper demonstrates how graphical models can identify mediating variables in causal pathways, specifically analyzing fatigue and weakness in people living with HIV, where traditional causal mediation analysis was inconclusive.

## Contribution

It introduces the application of graphical models to determine mediators in causal pathways within HIV research, providing a practical alternative to causal mediation analysis.

## Key findings

- Graphical models successfully identified fatigue as a mediator.
- Graphical models clarified the causal pathway between treatment, fatigue, and weakness.
- Traditional causal mediation analysis was inconclusive in this context.

## Abstract

We empirically demonstrate that graphical models can be a valuable tool in the identification of mediating variables in causal pathways. We make use of graphical models to elucidate the causal pathway through which the treatment influences the levels of fatigue and weakness in people living with HIV (PLHIV) based on a secondary analysis of a categorical dataset collected in a behavioral clinical trial: is weakness a mediator for the treatment and fatigue, or is fatigue a mediator for the treatment and weakness? Causal mediation analysis could not offer any definite answers to these questions.\\ KEYWORDS: Contingency tables; graphical models; loglinear models; HIV; mediation