This document is a brief on the 8 percent drop in the uninsurance rate which resulted from the addition of a verification question to the Current Population Survey (CPS) health insurance module. August 2001.

In March 2000, the Census Bureau added a verification question to the Current Population Survey (CPS) health insurance module. This question resulted in a more accurate estimate of the rate of uninsurance. This brief describes the Census Bureau’s previous approach to measuring health insurance and discusses the effect of introducing the verification component. August 2001.

This paper provides a brief overview of two approaches to correct for the effects of the Current Population Survey health insurance verification item when constructing a time series. October 2003.

Survey estimates of public health insurance program enrollment tend to be lower than those compiled from administrative enrollment data for those same programs, a discordance which is particularly apparent for Medicaid. The crude Medicaid undercount in the Current Population Survey’s Annual Social and Economic Supplement (CPS), the most prominently used survey for policy research that measures health insurance coverage, was 32 percent in both 2000 and 2001. Given the important uses of the CPS data, improved understanding of the undercount in the CPS is crucial. This paper presents parameters from two logistic regression models. These parameters can be used to predict the probability that the Medicaid administrative data imply that a CPS sample member actually had Medicaid. Originally published October 2007; revised with a minor code revision for Model 2 in November 2008 (revisions are reflected in the attachments).

The second download available on this page is a text file with the Stata code for this adjustment.

This document provides a description of the date processing error in the Current Population Survey that less to a misreporting of insurance coverage and the adjustment solution. In a small percentage of cases, some residents in a household were tabulated as "not covered" by insurance when they had in fact reported private or group coverage. This finding led to the Census Bureau’s recent downward revision of the number of uninsured from 15.9 to 15.3 percent or about 1.8 million fewer uninsured people in the U.S. in 2005. April 2007.