TALK: Network Time Series

Event Information

Share this event

Date and Time

Location

Location

D.314 Data Science Campus

Government Buildings

Cardiff Road

Newport

NP10 8XG

United Kingdom

View Map

Event description
This talk is part of the Data Science Campus Seminar Series

About this Event

THIS IS AN INTERNAL ONS EVENT ONLY – PLEASE REGISTER WITH YOUR ONS EMAIL ADDRESS

Failure to do so may result in your booking being cancelled.

Title: Network Time Series

Summary:

This talk is part of the Data Science Campus Seminar Series

A network time series is a multivariate time series where the individual series are known to be linked by some underlying network structure. Sometimes this network is known a priori, and sometimes the network has to be inferred, often from the multivariate series itself. Network time series are becoming increasingly common, long, and collected over a large number of variables. We are particularly interested in network time series whose network structure changes over time. We describe some recent developments in the modeling and analysis of network time series via generalised network autoregressive (GNAR) process models. The GNAR model relates values of a time series for a given variable and time to earlier values of the same variable and of neighbouring variables, within inclusion controlled by the network structure. We illustrate our GNAR models with examples from wind speed and international GDP time series. In the latter case, we show how GNAR techniques can infer a network and provide good forecasting performance, and we postulate the reasons for this. The paper associated with this talk can be downloaded from arXiv:1912.04758). The R package GNAR can be downloaded from CRAN.

Speaker: Guy Nason – Imperial College London

Date and Time

Location

D.314 Data Science Campus

Government Buildings

Cardiff Road

Newport

NP10 8XG

United Kingdom

View Map

Save This Event

Event Saved