Measuring Changes in Disparity Gaps: An Application to Health Insurance

TL;DR

This paper introduces a method to quantify and decompose changes in disparity gaps between groups, such as gender or racial groups, using treatment effect differences and decomposition techniques, applied to Medicare's impact on health insurance access.

Contribution

It presents a novel approach combining CATE differences and decomposition methods to analyze disparity reductions in program evaluations.

Findings

Medicare significantly reduces health insurance disparities.

Decomposition reveals the sources of disparity changes.

Method effectively isolates composition and effect-driven gap reductions.

Abstract

We propose a method for reporting how program evaluations reduce gaps between groups, such as the gender or Black-white gap. We first show that the reduction in disparities between groups can be written as the difference in conditional average treatment effects (CATE) for each group. Then, using a Kitagawa-Oaxaca-Blinder-style decomposition, we highlight how these CATE can be decomposed into unexplained differences in CATE in other observables versus differences in composition across other observables (e.g. the "endowment"). Finally, we apply this approach to study the impact of Medicare on American's access to health insurance.