Small Area Estimation of the Prevalence of Cancer Risk Factors and Screening via Bayesian Methods Using Combined Information from Two Surveys

• Activity Number: 342
• Type: Invited
• Date/Time: Tuesday, August 4, 2009 : 2:00 PM to 3:50 PM
• Sponsor: Section on Bayesian Statistical Science
• Author(s): William Davis and Eric Feuer and Van L. Parsons and Trivellore E. Raghunathan and Nathaniel Schenker*+ and Dawei Xie
• Companies: National Cancer Institute and National Cancer Institute and National Center for Health Statistics and University of Michigan and National Center for Health Statistics and University of Pennsylvania
• Keywords: Cancer surveillance ; Behavioral Risk Factor Surveillance System ; National Health Interview Survey ; Mammography ; Smoking ; Gibbs sampling

Abstract

Cancer surveillance requires estimates of the prevalence of cancer risk factors and screening for small areas such as counties or states. Two popular data sources are the Behavioral Risk Factor Surveillance System (BRFSS), a telephone survey conducted by state agencies, and the National Health Interview Survey (NHIS), an area probability sample survey conducted via face-to-face interviews. The BRFSS is larger and collects data from almost every county; but it has lower response rates and does not include subjects who live in households with no telephones. On the other hand, the NHIS is smaller and does not collect data from the majority of counties; but it includes both telephone and non-telephone households and has higher response rates. This talk describes work on using Bayesian methods to combine information from both surveys to incorporate their strengths into small-area estimates.