Sensitivity analysis for matching on high-dimensional predictors: A case study of racial disparity in US mortality

TL;DR

This paper investigates the challenges of high-dimensional matching for causal inference, using sensitivity analyses to study racial disparities in US mortality with detailed physical activity data.

Contribution

It introduces a sensitivity analysis framework for high-dimensional matching and applies it to analyze racial disparities in mortality using novel accelerometer-based physical activity measures.

Findings

Sensitivity of matching to implementation details highlighted

Main sources of variation and bias identified

Application demonstrates the impact of physical activity measurement on disparity analysis

Abstract

Matching on a low dimensional vector of scalar covariates consists of constructing groups of individuals in which each individual in a group is within a pre-specified distance from an individual in another group. However, matching in high dimensional spaces is more challenging because the distance can be sensitive to implementation details, caliper width, and measurement error of observations. To partially address these problems, we propose to use extensive sensitivity analyses and identify the main sources of variation and bias. We illustrate these concepts by examining the racial disparity in all-cause mortality in the US using the National Health and Nutrition Examination Survey (NHANES 2003-2006). In particular, we match African Americans to Caucasian Americans on age, gender, BMI and objectively measured physical activity (PA). PA is measured every minute using accelerometers for up to seven days and then transformed into an empirical distribution of all of the minute-level observations. The Wasserstein metric is used as the measure of distance between these participant-specific distributions.