Health Insurance Estimates from the CPS vs. ACS: An Analysis of State-Specific Program Names

• Activity Number: 331
• Type: Topic Contributed
• Date/Time: Tuesday, August 3, 2010 : 10:30 AM to 12:20 PM
• Sponsor: Social Statistics Section
• Author(s): Joanne Pascale*+
• Companies: U.S. Census Bureau
• Keywords: health ; insurance ; CPS ; ACS ; Medicaid

Abstract

The American Community Survey recently began measuring health insurance, prompting comparisons to the Current Population Survey. One difference is that the CPS embeds state-specific program names in questions about Medicaid coverage; the ACS does not. There is some concern that the lack of state-specific stimuli in the ACS may lead to underreporting of Medicaid. While it may seem self-evident that state-specific cues aid in reporting, there is little empirical evidence to support this. There is also considerable variation in the nature and number of state-specific program names across states, and little is known about the specific features of the cues that may prompt reporting accuracy. This paper examines the relationship between features of state-specific program names used in the CPS and (1) reporting accuracy in the CPS and (2) differences between CPS and ACS estimates of Medicaid.