Using ecological propensity score to adjust for missing confounders in small area studies.
Using ecological propensity score to adjust for missing confounders in small area studies.
复制标题
DOI：
10.1093/biostatistics/kxx058
复制
发表时间：
2019-01-01
期刊：
影响因子：
--
通讯作者：
Blangiardo M
中科院分区：
文献类型：
--
作者：
Wang Y;Pirani M;Hansell AL;Richardson S;Blangiardo M
在流行病学中，小区域生态研究通常用于评估区域一级风险因素对健康结果的影响，而这些数据只能以汇总的形式获得。然而，由于未测量的混杂因素，由此产生的估计经常是有偏差的，而这些混杂因素通常不能从用于这些研究的标准行政登记中获得。可以通过调查或队列等外部数据集提供关于混杂因素的额外信息，这些数据是在个人一级而不是在地区一级获得的；然而，这种数据通常缺乏行政登记册的地理覆盖面。我们开发了一个分析框架，它结合了来自不同来源的生态和个人水平的数据，以提供较少偏见的区域水平风险因素的调整估计。我们的方法(I)将所有可用的个体水平混杂因素总结为一个区域级别的标量变量，我们称之为生态倾向得分(EPS)，(Ii)实现了一种分层结构的方法来计算缺失的EPS的值，以及(Iii)将估计和推算的EPS包括到将风险因素与健康结果联系起来的生态回归中。通过模拟研究，我们表明，通过EPS将个体水平数据整合到小区域分析中是一种很有前途的方法，可以减少由于不可测量的混杂因素而导致的生态学研究固有的偏差；我们还将该方法应用于一个真实的案例研究，以评估空气污染对大伦敦地区冠心病住院人数的影响。
Small area ecological studies are commonly used in epidemiology to assess the impact of area level risk factors on health outcomes when data are only available in an aggregated form. However, the resulting estimates are often biased due to unmeasured confounders, which typically are not available from the standard administrative registries used for these studies. Extra information on confounders can be provided through external data sets such as surveys or cohorts, where the data are available at the individual level rather than at the area level; however, such data typically lack the geographical coverage of administrative registries. We develop a framework of analysis which combines ecological and individual level data from different sources to provide an adjusted estimate of area level risk factors which is less biased. Our method (i) summarizes all available individual level confounders into an area level scalar variable, which we call ecological propensity score (EPS), (ii) implements a hierarchical structured approach to impute the values of EPS whenever they are missing, and (iii) includes the estimated and imputed EPS into the ecological regression linking the risk factors to the health outcome. Through a simulation study, we show that integrating individual level data into small area analyses via EPS is a promising method to reduce the bias intrinsic in ecological studies due to unmeasured confounders; we also apply the method to a real case study to evaluate the effect of air pollution on coronary heart disease hospital admissions in Greater London.
登录
查看更多内容
影响因子：
4
作者：
Hughes RA;White IR;Seaman SR;Carpenter JR;Tilling K;Sterne JA
通讯作者：
Sterne JA
影响因子：
2
作者：
Rubin, Donald B.
通讯作者：
Rubin, Donald B.
影响因子：
5.7
作者：
MENG, XL
通讯作者：
MENG, XL
影响因子：
1.8
作者：
Gamerman, D;Moreira, ARB;Rue, H
通讯作者：
Rue, H
影响因子：
2.7
作者：
Besag, J;Kooperberg, C
通讯作者：
Kooperberg, C