Separable effects for adherence

TL;DR

This paper introduces separable effects for adherence, a new causal estimand that isolates medication effects from adherence issues, enabling more accurate effectiveness assessment when sustained use is difficult.

Contribution

It proposes a novel class of estimands called separable effects for adherence, along with algorithms and estimators, to address limitations of traditional per-protocol analyses.

Findings

Separable effects can eliminate adherence-related biases.

Causal graphs help evaluate assumptions for identification.

Semi-parametric estimators are developed for practical use.

Abstract

Comparing different medications is complicated when adherence to these medications differs. We can overcome the adherence issue by assessing effectiveness under sustained use, as in the usual causal `per-protocol' estimand. However, when sustained use is challenging to satisfy in practice, the usefulness of this estimand can be limited. Here we propose a different class of estimands: separable effects for adherence. These estimands compare modified medications, holding fixed a component responsible for non-adherence. Under assumptions about treatment components' mechanisms of effect, the separable effects estimand can eliminate differences in adherence. These assumptions are amenable to interrogation by subject-matter experts and can be evaluated using causal graphs. We describe an algorithm for constructing causal graphs for separable effects, illustrate how these graphs can be used to reason about assumptions required for identification, and provide semi-parametric weighted estimators.