Small Area Estimates for States, Counties, & Health Service Areas

These estimates use two surveys:

  • Behavioral Risk Factor Surveillance System (BRFSS)
  • National Health Interview Survey (NHIS)

The two surveys are combined using novel statistical methodology. This yields estimates for states that strengthen BRFSS results with the higher response rate and coverage of non-telephone households available from NHIS and bias-corrected estimates for counties by utilizing data from both surveys and information from other areas with similar characteristics.

Available estimates are for the time periods 1997-1999 and 2000-2003. Years were grouped to provide reasonable sample sizes in each area to inform our models.

Model-based estimates incorporate data from other areas with similar profiles, especially where sample sizes are small. See Limitations & Uses.

The model-based estimates produced and presented on this website are not directly estimated BRFSS or NHIS area level estimates, although BFRSS and NHIS data was incorporated into the models.


2007 SPAIG Award Winner – The American Statistical Association presented this award to the collaborating organizations responsible for developing the methodology for these estimates.

Your feedback is important. Please Contact Us if you have any questions or comments.