Simplifying the interpretation of continuous time models for spatio-temporal networks
Simplifying the interpretation of continuous time models for spatio-temporal networks
复制标题
DOI：
10.1007/s10109-020-00345-z
复制
发表时间：
2021-07
影响因子：
2.9
通讯作者：
S. C. Gadd;A. Comber;M. Gilthorpe;Keiran Suchak;A. Heppenstall
中科院分区：
文献类型：
--
作者：
S. C. Gadd;A. Comber;M. Gilthorpe;Keiran Suchak;A. Heppenstall
时间动态网络的自回归和移动平均模型将时间视为一系列离散步骤，假设数据测量之间的间隔均匀，如果不满足此假设，则可能引入偏差。本文使用来自伦敦地铁网络的真实和模拟数据，说明了使用连续时间多层模型来捕获边缘属性的时间轨迹，而无需同时测量，以及两种生成可解释的模型结果摘要的方法。其中包括提取时间模式的“特征”（例如最大值，最大值时间），这有助于理解每个连接的网络属性，并将整个网络属性总结为时间的连续函数，从而可以在任何时候估计网络属性，而无需同时测量的时间聚集。响应变量的时间模式特征的结果以合理的精度捕获。模型低估了暴露变量的时间模式特征的变化。这些模型显示出精度的不足。这两个模型总结都提供了清晰的“现实世界”解释，并可应用于一系列时空网络结构（如河流、社会网络）的数据。这些模型应该在一系列场景中进行更广泛的测试，并有可能进行改进，例如暴露变量维度中的随机效应。
Autoregressive and moving average models for temporally dynamic networks treat time as a series of discrete steps which assumes even intervals between data measurements and can introduce bias if this assumption is not met. Using real and simulated data from the London Underground network, this paper illustrates the use of continuous time multilevel models to capture temporal trajectories of edge properties without the need for simultaneous measurements, along with two methods for producing interpretable summaries of model results. These including extracting ‘features’ of temporal patterns (e.g. maxima, time of maxima) which have utility in understanding the network properties of each connection and summarising whole-network properties as a continuous function of time which allows estimation of network properties at any time without temporal aggregation of non-simultaneous measurements. Results for temporal pattern features in the response variable were captured with reasonable accuracy. Variation in the temporal pattern features for the exposure variable was underestimated by the models. The models showed some lack of precision. Both model summaries provided clear ‘real-world’ interpretations and could be applied to data from a range of spatio-temporal network structures (e.g. rivers, social networks). These models should be tested more extensively in a range of scenarios, with potential improvements such as random effects in the exposure variable dimension.