Diagnostic Process to Assess the Effects of Weighting BRFSS Data

• Activity Number: 341
• Type: Contributed
• Date/Time: Tuesday, July 31, 2007 : 2:00 PM to 3:50 PM
• Sponsor: Section on Survey Research Methods
• Author(s): Henry Roberts and Robert Woldman and Elizabeth Hughes and Ruth Jiles
• Companies: Centers for Disease Control and Prevention and North Carolina Department of Health and Human Services and Northup Gruman Inc and Centers for Disease Control and Prevention
• Keywords: BRFSS ; Weighting-Class Variables ; Nonresponse Bias ; Nonsampling Error ; Standard Error

Abstract

This research focuses on developing a diagnostic process that assesses the accuracy, robustness, and precision of the BRFSS prevalence estimates. This diagnostic process has three distinct sequential assessments: accuracy, robustness, precision. This diagnostic process serves to enhance the present BRFSS data quality monitoring processes. The 2004 NC BRFSS yielded accurate estimates of the proportion of: adult males and females, adults ages 18-34, 35-54, and 55+; less accurate estimates of the proportion of Hispanic adults, married adults, and adult high school graduates were also observed. Overall, robust and equally precise prevalence estimates were observed for six of the eight selected public health outcomes of interest. These robust and equally precise prevalence estimates provided evidence of negligible effects of errors due to disproportionate sampling rates, on response bias.