Improving the Socioeconomic Ranking of Small Areas Using the Estimates from the American Community Survey

• Activity Number: 345
• Type: Contributed
• Date/Time: Tuesday, August 5, 2014 : 10:30 AM to 12:20 PM
• Sponsor: Social Statistics Section
• Author(s): Mandi Yu*+ and Jun Luo and Li Zhu
• Companies: National Cancer Institute and Information Management Services and National Cancer Institute
• Keywords: sampling error ; health disparity ; monte-carlo ; cancer incidence ; composite SES index ; area-based SES

Abstract

As substitutes for individual-based information, area-based socioeconomic status (SES) measures have demonstrated their usefulness in population-based research on cancer health disparities. However, the uncertainty in such measurement estimates due to survey sampling is usually ignored. This methodological limitation could have affected on the relative SES rankings of small areas, consequently distorted the estimation of the relationships between certain SES measures and cancer health outcomes. Because the American Community Survey is based on a smaller sample of the U.S. population than the Decennial Census Long Form Survey, such impact could be larger. To address this challenge, we explore the use of a Monte-Carlo approach to quantify the precision of estimating the quantile rankings of census tracts for a composite SES index that is constructed using several census tract-based SES measures based on factor analyses. We further assess the amount of uncertainty in estimating the rates of cancer incidence for SES quantile groups attributable to the uncertainties in ranking census tracts. Preliminary results show that compared to the traditional approach where area-based SES estimate