Statistical Methods for Imputing Race and Ethnicity

SOA Research Institute Societal Purpose

April 2024

Authors

Larry Baeder
Erica Baird, PhD, FSA, MAAA
Peggy Brinkmann, FCAS, MAAA
Joe Long, ASA, MAAA
Caleb Stracke, ASA, MAAA
Kweweli Togba-Doya
Gabriele Usan
Natalie Weaver
Meseret Woldeyes, MS
Milliman

Description

This paper describes a range of techniques for developing probabilistic estimates or predictions of individual race and/or ethnicity. The authors apply some methods to data from an insurance application and compare them with a focus on relative accuracy and potential bias. Lastly, the authors apply some of these methods to a simulated dataset to illustrate how to use them in practice.

Report

Statistical Methods for Imputing Race and Ethnicity

Tutorial Files

Tutorial Dataset

Webcast

Statistical Methods for Imputing Race and Ethnicity 

Podcast

Statistical Methods for Imputing Race and Ethnicity

Acknowledgments

The researchers’ deepest gratitude goes to those without whose efforts this project could not have come to fruition: the Project Oversight Group and others for their diligent work overseeing, reviewing, and editing this report for accuracy and relevance.

Project Oversight Group members:
Dorothy Andrews, Ph.D., ASA, MAAA, CSPA
Brian Bayerle, FSA, MAAA
Stephen Cameron, FSA, MAAA
Amine Elmeghni, FSA, MAAA, MSc
Jean-Marc Fix, FSA, MAAA
Hannah Kraus, ASA, MAAA
Tim Luedtke, FSA, MAAA
Ian McCulla, FSA, MAAA
Andrew Melnyk
Min Mercer, FSA
Murali Niverthi, FSA, MAAA
Renee West, FSA, MAAA

At the Society of Actuaries Research Institute:
Lisa Schilling, FSA, EA, FCA, MAAA, Director of Practice Research

Questions or comments?

Give us your feedback! Take a short survey on this report: Take Survey