Coverage properties of 95% confidence intervals for commonly used measures of health disparity implemented in HD*Calc

• Activity Number: 495 - Collaborative Research on Measures of Health Disparities
• Type: Topic Contributed
• Date/Time: Wednesday, August 2, 2017 : 10:30 AM to 12:20 PM
• Sponsor: Section on Statistical Consulting
• Author(s): Jaeil Ahn* and George Luta and Benmei Liu and Eric Feuer and Mandi Yu and Sam Harper
• Companies: and Georgetown University and National Cancer Institute and National Cancer Institute and National Cancer Institute and McGill University
• Keywords: health disparity ; HD*calc ; standard error ; Taylor series ; confidence interval

Abstract

There is increased interest in eliminating health disparity in U.S. (e.g., Healthy People 2020) and world-wide. Broadly defined, health disparity refers to inequalities in health status related to ethnicity, socioeconomic status, education, environment, and geographic locations. To make informed health policy decisions, it is essential to properly measure disparities and assess their trend over time. HD*Calc is a free statistical software that implements eleven most commonly used measures of health disparity and provides corresponding 95% confidence intervals. However, evaluations of the performance of these confidence intervals are lacking. Through a comprehensive simulation study we have evaluated the coverage properties of these confidence intervals. We also illustrate the use of HD*Calc with age-adjusted cancer incidence rates at the national, state, and county level.