Generalized Network Autoregressive Processes and the GNAR Package

Marina Knight, Kathryn Leeming, Guy Nason, Matthew Nunes

Main Article Content

Abstract

This article introduces the GNAR package, which fits, predicts, and simulates from a powerful new class of generalized network autoregressive processes. Such processes consist of a multivariate time series along with a real, or inferred, network that provides information about inter-variable relationships. The GNAR model relates values of a time series for a given variable and time to earlier values of the same variable and of neighboring variables, with inclusion controlled by the network structure. The GNAR package is designed to fit this new model, while working with standard 'ts' objects and the igraph package for ease of use.

Article Details

Article Sidebar