Improved Small Area Inference from Data Integration Using Global-Local Priors

TL;DR

This paper introduces a hierarchical global-local prior approach to enhance small area inference by integrating multiple data sources, demonstrated through improved estimation of health insurance coverage in Florida counties.

Contribution

It extends existing data integration methods by applying hierarchical global-local priors, specifically horseshoe priors, to improve small area parameter inference from multiple data sources.

Findings

Horseshoe priors outperform lasso priors in model performance.

The methodology provides more accurate small area estimates.

Simulation results confirm improved inference with data integration.

Abstract

We present and apply methodology to improve inference for small area parameters by using data from several sources. This work extends Cahoy and Sedransk (2023) who showed how to integrate summary statistics from several sources. Our methodology uses hierarchical global-local prior distributions to make inferences for the proportion of individuals in Florida's counties who do not have health insurance. Results from an extensive simulation study show that this methodology will provide improved inference by using several data sources. Among the five model variants evaluated the ones using horseshoe priors for all variances have better performance than the ones using lasso priors for the local variances.