Some experiments on network time series

Dr Matthew Nunes, University of Bath. Part of the Statistics Seminar Series.

In this talk I consider analysis problems for time series that are observed at nodes of a potentially large network structure. Such problems commonly appear in a vast array of fields, such as environmental data or epidemiology, or measurements from computer system monitoring. The time series observed on the network might exhibit different characteristics such as nonstationary behaviour or strong correlation, and the nodal series evolve according to the inherent "network-spatial" structure.

We will introduce the network autoregressive / moving average processes: a set of flexible models for network time series. Our models are especially useful when the structure of the graph, associated with the multivariate time series, changes over time. Such network topology changes are invisible to standard VARMA-like models. For integrated network time series models we introduce network differencing based on a network lifting (wavelet) transform and remark on some of its properties. We demonstrate our techniques on some real data for some example analysis tasks for network time series.