Combining Data from the NHIS and BRFSS

描述(由申请人提供) 癌症监测研究需要在小区域水平上对风险因素进行准确估计。这些风险因素通常从国家健康访谈调查(NHIS)或行为风险因素监测调查(BRFSS)等调查中获得。不幸的是，没有一项以人群为基础的调查提供了此类风险因素的理想患病率估计。一种策略是结合多项调查的信息，利用一项调查的互补优势来弥补另一项调查的弱点。NHIS是一项具有全国代表性的面对面调查，回复率很高；然而，由于样本量太小，它无法对州或州以下的风险因素流行率进行估计。BRFSS是一项州级电话调查，排除了非电话家庭，回复率较低，但确实在所有州和许多国家提供了合理的样本量。有几种方法可用于构造结合来自NHIS和BRFSS的信息的小区域估计器，包括直接估计器、分层贝叶斯模型下的估计器和模型辅助估计器。该项目将侧重于后者，其中包括使用BRFSS数据和NHIS数据集得出的控制总数构建广义回归(GREG)估计量，重新加权计划以减少BRFSS和NHIS数据集中抽样元素之间的距离度量，以及利用现有和新开发的技术通过加权和小区域平滑技术平滑所产生的估计。这种方法特别有前景，因为与其他建议的技术不同，它可以使用现有的公开数据来应用。

DESCRIPTION (provided by applicant) Cancer surveillance research requires accurate estimates of risk factors at the small area level. These risk factors are often obtained from surveys such as the National Health Interview Survey (NHIS), or the Behavioral Risk Factors Surveillance Survey (BRFSS). Unfortunately, no one population-based survey provides ideal prevalence estimates of such risk factors. One strategy is to combine information from multiple surveys, using the complementary strengths of one survey to compensate for the weakness of the other. The NHIS is a nationally representative, face-to-face survey with a high response rate; however, it cannot produce state or sub-state estimates of risk factor prevalence because sample sizes are too small. The BRFSS is a state-level telephone survey that excluded non-telephone households and has a lower response rate, but does provide reasonable sample sizes in all states and many countries. Several methods are available for constructing small-area estimators that combine information from both the NHIS and the BRFSS, including direct estimators, estimators under hierarchical Bayes models and model-assisted estimators. The project will focus on the latter, which includes constructing generalized regression (GREG) estimators using BRFSS data and control totals derived from the NHIS dataset, re-weighting schemes to reduce distance measures between sampled elements in BRFSS and NHIS datasets, and the use of existing and newly developed techniques to smooth the resulting estimates using weighting and small-area smoothing techniques. This approach is particularly promising because, in contrast to other proposed techniques, it can be applied using existing publicly available data.