The CPS ASEC provides the most timely and accurate national data on health insurance with income detail. Hence, it is the preferred source for national analysis. The ACS is preferred for subnational data on health insurance by detailed demographic characteristics, due to its large sample size. The Census Bureau recommends using the ACS for single-year estimates of health insurance at the state level. Users looking for consistent, state-level trends before 2008 should use the CPS ASEC.
For sub-state areas such as counties, users should consider their specific needs when picking the appropriate data source. The SAHIE program produces single-year estimates of number and percent insured/uninsured by some demographic and income groups. SAHIE has standard errors mostly smaller than direct survey estimates. Therefore, SAHIE is the preferred source if it produces estimates for all of your characteristics of interest. Users who need estimates of health insurance coverage by other characteristics such as occupation should use the ACS, where and when available.
The SIPP is the only Census-provided source of longitudinal health insurance coverage estimates. It provides national estimates, as well as estimates for some larger states. As SIPP collects monthly data over 2 ½ to 4 year panels, it is also a source of health insurance coverage estimates for a time period of more or less than one year.
Note that Figure 1 is a summary of general recommendations. There are a number of considerations users should take into account when selecting a data source. For example, it is generally advisable to use the same data source for a particular purpose across all levels of geography.
The National Health Interview Survey (NHIS) is collected by the Census Bureau and released by the National Center for Health Statistics (NCHS). The Census Bureau recommends the NHIS when examining health outcomes. Links to the NHIS and other surveys that currently collect or have collected health insurance data can be found at Related Sites. Please note the list of external surveys is not exhaustive.
The Census Bureau produces health insurance data from three surveys and one model-based program. Depending on your needs, one data source may be more suitable than another data source. Below are some basic differentiations between each source.
The chart below summarizes the recommendations at various geographic levels:
Figure 1. U.S. Census Bureau Health Insurance Data Source Recommendations
|Geographic Level||Cross-Sectional Estimates||Longitudinal Estimates|
|United States||CPS ASEC for income
ACS for detailed race groups
|State||ACS/CPS ASEC 2-year averages 1||SIPP (selected states)|
|Substate (areas with populations of 65,000 or more)||SAHIE for counties, else
ACS 1-year period estimates
|Substate (areas with populations of 20,000 to 65,000)||SAHIE for counties, else
ACS 3-year period estimates2
|Substate (areas with populations less than 20,000)||SAHIE for counties, else
ACS 5-year period estimates 3