Referent selection in case-crossover analyses of acute health effects of air pollution
Referent selection in case-crossover analyses of acute health effects of air pollution
复制标题
DOI：
10.1097/00001648-200103000-00010
复制
发表时间：
2001-03-01
期刊：
影响因子：
5.4
通讯作者：
Checkoway, H
中科院分区：
文献类型：
--
作者：
Levy, D;Lumley, T;Checkoway, H
病例交叉设计是为了研究间歇性接触对一种罕见的急性发作疾病随后发生的短暂影响。这一设计可以替代泊松时间序列回归，用于研究细颗粒物空气污染对健康的影响。颗粒物的时间序列特征，包括长期趋势、季节趋势和短期自相关性，要求他在病例交叉设计中选择参照物，并对其进行调整，以最大限度地减少偏差。我们进行了模拟，以评估与不同参照者选择策略相关的偏倚，以进行拟议的病例交叉研究，研究颗粒物与原发性心脏骤停之间的关系。一些先验合理的策略与高达10%的相对偏差相关，但对于大多数策略，相对偏差小于2%，可信区间覆盖在名义水平的10%以内。我们发现，病例交叉设计的参照选择与时间序列分析中平滑方法的选择提出了相同的问题。此外，条件Logistic回归分析对于一些病例交叉设计不是严格有效的，从而引入了进一步的偏差。
The case-crossover design was proposed for the study of a transient effect of an intermittent exposure on the subsequent occurrence of a rare acute onset disease. This design can be an alterative to Poisson time series regression for studying the health effects of fine particulate matter air pollution. Characteristics of time-series of particulate matter, including longterm time trends, seasonal trends, and short-term autocorrelations, require that referent selection in the case-crossover design he considered carefully and adapted to minimize bias. We performed simulations to evaluate the bias associated with various referent selection strategies for a proposed case-cross-over study of associations between particulate matter and primary cardiac arrest. Some a priori reasonable strategies were associated with a relative bias as large as 10%, but for most strategies the relative bias was less than 2% with confidence interval coverage within 10% of the nominal level. We show that referent selection for case-crossover designs raises the same issues as selection of smoothing method for time series analyses. In addition, conditional logistic regression analysis is not strictly valid for some case-crossover designs, introducing further bias.