Statistical Inference on Health Disparity Indices for Complex Surveys

摘要: The National Cancer Institute developed the Health Disparities Calculator (HD*Calc) to facilitate research on health disparities. HD*Calc calculates multiple measures of disparities using data collected from population-based disease surveillance systems, such as cancer registries. In this paper, we extend use complex survey by developing plug-in point estimators and Taylor linearization variance that consider designs: stratification, multistage clustering, differential weighting. Our simulation indicates are approximately unbiased accurate. Using 2011-2016 Nutrition Examination Survey, demonstrate these in evaluating socioeconomic prevalence child adolescent (ages 2-18 years) obesity United States. Statistical software has been for ease disparity analyses data.