Assessing the Accuracy of Survey Reports of Health Insurance Coverage Using Enrollment Data
U.S. Census Bureau researcher Joanne Pascale, University of Minnesota researcher Angela Fertig, and SHADAC researcher Kathleen T. Call recently published a new article in the Health Services Research journal that details their efforts to measure the accuracy of responses to health insurance coverage surveys - such as the U.S. Census Bureau's Current Population Survey (CPS) - in reporting health insurance coverage and features of coverage for the civilian noninstitutionalized population. A reverse record check using a stratified random sample of enrollment records from households known to have health insurance through one large regional insurer and were cross-examined with data from the 2015 CPS survey in order to determine whether source/type of health insurance coverage were accurately self-reported by respondents of the survey.
Additionally, the Census Bureau redesigned the CPS in 2015 in order to make the survey more user-friendly, changing questions regarding individual features of insurance coverage from seeking "yes or no" answers to more open-ended and detailed toward the source of coverage that is reported by the respondent in order to capture more detailed information. The article thus additionally examines the accuracy of these individual questions, using comparable data from the Medical Expenditure Panel Survey (MEPS), the National Health Interview Survey (NHIS), and the Health Reform Monitoring Survey.