The Measurement of Medicaid Coverage in the SIPP : Evidence from a Comparison of Matched Records

This paper studies the accuracy of reported Medicaid coverage in the Survey of Income and Program Participation (SIPP) using a unique data set formed by matching SIPP survey responses to administrative records from the State of California. Overall, we estimate that the SIPP underestimates Medicaid coverage in the California population by about 10 percent. The probability that a SIPP respondent who is covered by Medicaid in a given month correctly reports their coverage is around 85 percent. The corresponding probability for low-income children is higher – around 90 percent. Under-reporting by those who are actually in the Medicaid system is partially offset by over-reporting of coverage by people who are not. Some of these false positive responses are attributable to errors and missing data in the administrative system, rather than to problems in the SIPP. Taking account of these errors, the estimated false positive rate for the population as a whole is about 1.5 percent, and 4-5 percent for poor children.