The moving-window Bayesian maximum entropy framework: estimation of PM(2.5) yearly average concentration across the contiguous United States.

The moving-window Bayesian maximum entropy framework: estimation of PM(2.5) yearly average concentration across the contiguous United States.
复制标题

DOI:
10.1038/jes.2012.57
复制
发表时间:
2012-09
影响因子:
4.5
通讯作者:
--
中科院分区:
医学3区
文献类型:
--
作者:

文献摘要

参考文献

被引文献

相似文献

地统计方法广泛用于估计空气污染流行病学研究的长期暴露,尽管它们处理大地理区域的空间非平稳性以及与缺失监测数据相关的不确定性的能力有限。我们开发了移动窗口 (MW) 贝叶斯最大熵 (BME) 方法,并应用该框架来估计美国本土细颗粒物 (PM2.5) 年平均浓度。MW 方法解释了空间非平稳性,而 BME 方法严格处理与空气监测系统中数据缺失相关的不确定性。在对 2003 年一组随机选择的完整 PM2.5 数据和不同程度缺失数据的模拟数据进行的交叉验证分析中,我们证明,单独使用 MW 方法可以使每年 PM2.5 估算的均方误差 (MSE) 减少至少 17.8%。此外,MWBME方法进一步将MSE降低了8.4%至43.7%,不完整数据比例从18.3%增加至82.0%。 MWBME 方法可显着减少估计误差,因此建议用于流行病学研究,以调查长期暴露于具有预期空间非平稳性的大地理区域的 PM2.5 的影响。
Geostatistical methods are widely used in estimating long-term exposures for air pollution epidemiological studies, despite their limited capabilities to handle spatial non-stationarity over large geographic domains and uncertainty associated with missing monitoring data. We developed a moving-window (MW) Bayesian Maximum Entropy (BME) method and applied this framework to estimate fine particulate matter (PM2.5) yearly average concentrations over the contiguous U.S. The MW approach accounts for the spatial non-stationarity, while the BME method rigorously processes the uncertainty associated with data missingnees in the air monitoring system. In the cross-validation analyses conducted on a set of randomly selected complete PM2.5 data in 2003 and on simulated data with different degrees of missing data, we demonstrate that the MW approach alone leads to at least 17.8% reduction in mean square error (MSE) in estimating the yearly PM2.5. Moreover, the MWBME method further reduces the MSE by 8.4% to 43.7% with the proportion of incomplete data increased from 18.3% to 82.0%. The MWBME approach leads to significant reductions in estimation error and thus is recommended for epidemiological studies investigating the effect of long-term exposure to PM2.5 across large geographical domains with expected spatial non-stationarity.
DOI: 10.1056/nejmsa0805646
发表时间: 2009-01-22
期刊: The New England journal of medicine
影响因子: --
作者:
Pope CA 3rd;Ezzati M;Dockery DW
通讯作者: Dockery DW
DOI: 10.1007/bf00890661
发表时间: 1990-10-01
期刊: MATHEMATICAL GEOLOGY
影响因子: --
作者:
CHRISTAKOS, G
通讯作者: CHRISTAKOS, G
DOI: 10.1080/15287390802445483
发表时间: 2009-01-01
影响因子: 2.6
作者:
Liao, Duanping;Whitsel, Eric A.;Anderson, Garnet
通讯作者: Anderson, Garnet
DOI: 10.1289/ehp.11692
发表时间: 2009-04
影响因子: 10.4
作者:
Yanosky JD;Paciorek CJ;Suh HH
通讯作者: Suh HH
美国健康效应研究中PM(2.5)化学成分的空间和时间变化。
DOI: 10.1289/ehp.9621
发表时间: 2007-07
影响因子: 10.4
作者:
Bell ML;Dominici F;Ebisu K;Zeger SL;Samet JM
通讯作者: Samet JM