Health Insurance Estimates from the ACS: An Analysis of Directly Purchased Coverage

• 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): Victoria Lynch*+
• Companies: The Urban Institute
• Keywords: ACS ; health insurance

Abstract

Survey methods are known to impact estimates used to shape public policy on health insurance. There is evidence that coverage rates are higher when surveys ask about specific types of coverage and verify reports of no insurance. There is also evidence that respondents in surveys with relatively extensive questioning about coverage-related topics are more accurate reporting Medicaid enrollment. The American Community Survey (ACS) collects most responses by mail so there is little opportunity for tailoring the interview to help the respondent accurately report coverage. ACS estimates of consumer purchased coverage are higher than other surveys. This paper will examine how ACS estimates might be impacted if interviewers and post-collection processing had the opportunity to use income, employment, and other data that can imply eligibility/coverage to modify reports of purchased coverage.