Network double autoregression

TL;DR

This paper introduces the network double autoregression (NDAR) model, which effectively captures high-dimensional, network-structured, and heteroscedastic time series data, with proven asymptotic properties and practical stock data applications.

Contribution

The paper develops the NDAR model combining network structure and double autoregression, with estimation, asymptotic analysis, and model selection methods.

Findings

Model performs well with moderate dimensions and network sizes.

Asymptotic properties of estimators are established.

Applied successfully to stock data analysis.

Abstract

Modeling high-dimensional time series with simple structures is a challenging problem. This paper proposes a network double autoregression (NDAR) model, which combines the advantages of network structure and the double autoregression (DAR) model, to handle high-dimensional, conditionally heteroscedastic, and network-structured data within a simple framework. The parameters of the model are estimated using quasi-maximum likelihood estimation, and the asymptotic properties of the estimators are derived. The selection of the model's lag order will be based on the Bayesian information criterion. Finite-sample simulations show that the proposed model performs well even with moderate time dimensions and network sizes. Finally, the model is applied to analyze three different categories of stock data.