Bayesian Record Linkage with Variables in One File

TL;DR

This paper introduces an extended Bayesian record linkage method that incorporates variables unique to each file, improving linkage accuracy and inference in multi-file data scenarios, especially relevant in healthcare and social sciences.

Contribution

The paper extends existing Bayesian record linkage techniques to include associations between variables exclusive to each file, enhancing linkage accuracy and inference.

Findings

Method improves linkage accuracy in simulations.

Incorporating exclusive variables yields more precise inferences.

Application to real data demonstrates practical utility.

Abstract

In many healthcare and social science applications, information about units is dispersed across multiple data files. Linking records across files is necessary to estimate the associations of interest. Common record linkage algorithms only rely on similarities between linking variables that appear in all the files. Moreover, analysis of linked files often ignores errors that may arise from incorrect or missed links. Bayesian record linking methods allow for natural propagation of linkage error, by jointly sampling the linkage structure and the model parameters. We extend an existing Bayesian record linkage method to integrate associations between variables exclusive to each file being linked. We show analytically, and using simulations, that this method can improve the linking process, and can yield accurate inferences. We apply the method to link Meals on Wheels recipients to Medicare Enrollment records.