Monitoring Count Time Series in R: Aberration Detection in Public Health Surveillance
Monitoring Count Time Series in R: Aberration Detection in Public Health Surveillance
复制标题
DOI：
10.18637/jss.v070.i10
复制
发表时间：
2016-05-01
影响因子：
5.8
通讯作者：
Hohle, Michael
中科院分区：
文献类型：
--
作者：
Salmon, Maelle;Schumacher, Dirk;Hohle, Michael
公共卫生监测的目的是减轻疾病负担，例如，在发生传染病时及时发现新出现的疫情。从统计角度看，这意味着使用适当的方法监测汇总病例报告的时间序列。本文介绍了R包监视提供的这种自动像差检测工具。我们介绍了监控时间序列的可视化、建模和监控功能。在建模方面，重点介绍了基于广义线性模型、多元广义线性模型、广义加性模型和广义加性模型的单变量时间序列建模。这种建模的应用包括举例说明公知的Farrington算法的实现改进和扩展，例如通过样条法建模或通过在贝叶斯上下文中处理它。此外，我们使用贝塔二项式或狄利克雷多项式模型来研究分类时间序列并解决过度分散问题。关于监测，我们认为检测器要么基于休哈特式的观测计数和预测分布之间的单一时间点比较，要么基于似然比的累积和方法。最后，我们通过将监测集成到公共卫生机构的监测工作流程中，说明了监测如何在实践中支持异常检测。综上所述，本文展示了在公共卫生监测背景下，监测如何能够很好地支持自动异常检测。
Public health surveillance aims at lessening disease burden by, e.g., timely recognizing emerging outbreaks in case of infectious diseases. Seen from a statistical perspective, this implies the use of appropriate methods for monitoring time series of aggregated case reports. This paper presents the tools for such automatic aberration detection offered by the R package surveillance. We introduce the functionalities for the visualization, modeling and monitoring of surveillance time series. With respect to modeling we focus on univariate time series modeling based on generalized linear models (GLMs), multivariate GLMs, generalized additive models and generalized additive models for location, shape and scale. Applications of such modeling include illustrating implementational improvements and extensions of the well-known Farrington algorithm, e.g., by spline-modeling or by treating it in a Bayesian context. Furthermore, we look at categorical time series and address overdispersion using beta-binomial or Dirichlet-multinomial modeling. With respect to monitoring we consider detectors based on either a Shewhart-like single timepoint comparison between the observed count and the predictive distribution or by likelihood-ratio based cumulative sum methods. Finally, we illustrate how surveillance can support aberration detection in practice by integrating it into the monitoring workflow of a public health institution. Altogether, the present article shows how well surveillance can support automatic aberration detection in a public health surveillance context.