![IconGems-Print](images/IconGems-Print.png)
340 – SPEED: Applications of Advanced Statistical Techniques in Complex Survey Data Analysis: Small Area Estimation, Propensity Scores, Multilevel Models, and More
Comparing Direct Survey and Small Area Estimates of Health Care Coverage in New York
Jeniffer Iriondo-Perez
RTI International
Rachel Harter
RTI International
Amang Sukasih
RTI International
The Behavioral Risk Factor Surveillance Survey (BRFSS) is designed to produce estimates for states and large metropolitan areas. For some variables, county-level BRFSS estimates have been produced by others using small area estimation methodology. We generated county-level estimates of the proportion of adults with health insurance coverage (insured rate) using the New York BRFSS data. The goal was to demonstrate the small area estimation (SAE) technique using the readily-available R package BayesSAE. As a validation, we compared the results from BayesSAE with those from OpenBUGS, a well-established software for Bayesian computation. We also compared the model-based estimates with direct design-based estimates.