Estimates of Multiple Health Insurance Coverage in the American Community Survey

• Activity Number: 660
• Type: Contributed
• Date/Time: Thursday, August 4, 2011 : 10:30 AM to 12:20 PM
• Sponsor: Section on Government Statistics
• Author(s): Annie Linn Mach*+ and Brett O'Hara
• Companies: U.S. Census Bureau and U.S. Census Bureau
• Keywords: American Community Survey ; Health insurance

Abstract

The purpose of this paper is to investigate the American Community Survey (ACS) estimates of multiple types of coverage in the non-elderly population. Due to the costs associated with private health insurance and the eligibility restrictions associated with public coverage, it is unlikely that a person has multiple types of comprehensive coverage at a single point in time. Still, estimates from the 2009 ACS indicate that 7.2 percent of the insured non-elderly population has multiple types of coverage. This estimate suggests that the ACS is capturing more information than just comprehensive health insurance coverage. This paper examines pathways to multiple types of coverage, and identifies the most common occurrences of multiple types of coverage. This paper uses multinomial logistic regression to predict multiple types of coverage using the characteristics of the person (by ages 0-17 and 18-64) as well socioeconomic indicators. This paper includes a discussion of properly capturing comprehensive health insurance coverage in the ACS.