U.S. flag

An official website of the United States government

Skip Header

Health Insurance Data Revision

Revised CPS ASEC Health Insurance Data - released September 2011 - User Note

Data from the 2000-2010 Current Population Survey (CPS) Annual Social and Economic Supplement (ASEC) data have been revised to improve the consistency of estimates for the insured and uninsured as part of ongoing efforts to improve the quality of Census Bureau data. The CPS asks about health insurance coverage in the previous year (for example, the 2010 survey asked about coverage in 2009).


Revised calendar-year coverage estimates for 1999 to 2009 reflect the results of enhancements to the editing process, including the assignment of a family health plan to all individuals in the household and the addition of a new variable to the allocation matrix. The revisions were necessary to address the differences between the way that health insurance coverage is collected in the CPS ASEC and the way it is imputed.

Research has shown that individuals report more extensive dependent coverage than we impute. The number of dependents with coverage was much lower for those who were imputed than for those who reported coverage. Prior to the change in the editing process, if it was determined that a policyholder had a family health insurance plan, coverage was assigned to that individual’s spouse and/or children. With the revised edits, in these cases, coverage is assigned to everyone in the household.

Another change involves the allocation process. Previously, "private coverage status" was not used in the allocation matrix. This resulted in more dual-coverage individuals (i.e., people that had both public and private coverage) when coverage was allocated than when it was reported. To remedy this, a variable was created and added to the allocation matrices for the presence of private coverage. This resulted in revised estimates of public coverage and less dual coverage.

New Process Improves Health Insurance Coverage Data

The new editing process allows production of more accurate coverage data. The effect was to reduce the uninsured rate by 0.6 percentage points for calendar-year 2009. In September 2010, when the Census Bureau released the original estimates for 2009, an increase was reported in the percentage of uninsured between 2008 and 2009 from 14.9 percent to 16.1 percent. As shown in the revised tables, while the percentage of uninsured is lower than the original percentage for both 2008 and 2009, there is still a comparable increase in the percentage of uninsured.


Back to Header