PRACTICAL LARGE-SCALE SPATIO-TEMPORAL MODELING OF PARTICULATE MATTER CONCENTRATIONS
PRACTICAL LARGE-SCALE SPATIO-TEMPORAL MODELING OF PARTICULATE MATTER CONCENTRATIONS
复制标题
DOI：
10.1214/08-aoas204
复制
发表时间：
2009-03-01
影响因子：
1.8
通讯作者：
Suh, Helen H.
中科院分区：
文献类型：
--
作者：
Paciorek, Christopher J.;Yanosky, Jeff D.;Suh, Helen H.
过去二十年，科学和监管部门对颗粒物 (PM) 对健康的影响产生了浓厚的兴趣。描述个人长期暴露特征的有影响力的流行病学研究依赖于空间和时间上稀疏的监测数据，因此他们经常将相同的暴露分配给大地理区域和跨时间的参与者。我们估计了 1988 年至 2002 年期间大空间域中的每月 PM，用于研究护士健康研究中的健康影响。我们开发了一个概念上简单的时空模型，该模型使用一组丰富的协变量。该模型用于估计整个时间段的 PM10 浓度和该时间段子集的 PM2.5 浓度。在此期间的早期（1988 年至 1998 年），几乎没有 PM2.5 监测器在运行，因此我们开发了一个简单的模型扩展，该模型根据 PM10 模型预测有条件地表示 PM2.5。在流行病学分析中，与使用更简单的方法来估计暴露量相比，PM10 的模型预测与健康影响的相关性更强。我们的建模方法支持估计精细尺度和大规模空间异质性的应用，并通过使用每月变化的空间表面来捕获时空相互作用。同时，该模型在计算上是可行的，可以使用标准软件实现，并且易于科学受众理解。尽管简化了假设，该模型仍具有良好的预测性能和不确定性表征。
The last two decades have seen intense scientific and regulatory interest in the health effects of particulate matter (PM). Influential epidemiological studies that characterize chronic exposure of individuals rely on monitoring data that are sparse in space and time, so they often assign the same exposure to participants in large geographic areas and across time. We estimate monthly PM during 1988-2002 in a large spatial domain for use in studying health effects in the Nurses' Health Study. We develop a conceptually simple spatio-temporal model that uses a rich set of covariates. The model is used to estimate concentrations of PM10 for the full time period and PM2.5 for a subset of the period. For the earlier part of the period, 1988-1998, few PM2.5 monitors were operating, so we develop a simple extension to the model that represents PM2.5 conditionally on PM10 model predictions. In the epidemiological analysis, model predictions of PM10 are more strongly associated with health effects than when using simpler approaches to estimate exposure.Our modeling approach supports the application in estimating both fine-scale and large-scale spatial heterogeneity and capturing space-time interaction through the use of monthly-varying spatial surfaces. At the same time, the model is computationally feasible, implementable with standard software, and readily understandable to the scientific audience. Despite simplifying assumptions, the model has good predictive performance and uncertainty characterization.