Work

Unequal enforcement, unequal inference: rethinking how we define policy exposures

Year: 2025

Type: article

Abstract: Social policy is a powerful intervention that has the potential to reduce or widen inequities in population health. While studies estimating the causal effect of social policies on health are valuable to policy stakeholders, these studies frequently report unstratified estimates for the total population, even though differential enforcement by sub-unit populations and geographies is common. The analytical decision to report unstratified estimates assumes a single version of the social policy is implemented uniformly across populations; in the presence of biased implementation, these analyses can generate misleading results that impede meaningful policy evaluation. In this commentary, we highlight the importance of considering differential policy effects among subpopulations as a function of poorly defined policy exposure (ie, lack of causal consistency) rather than effect measure modification or mediation. Framing the issue as one of poorly defined policy exposure allows for critical disentangling of the explicit and implicit purposes of a policy.

Source: Health Affairs Scholar

DOI: 10.1093/haschl/qxaf063

Authors: Simone Wien, Ariana N Mora, Michael R Kramer

Institutions: Emory University, Mercer University, Mercer University Health Sciences Center

Language: English

Topic: Advanced Causal Inference Techniques

Subfield: Statistics and Probability

Field: Mathematics

Domain: Physical Sciences

SDGs: Reduced inequalities, Good health and well-being

Open Access status: gold

Estimated APC paid: $3,150