Comparative Analysis of Spatiotemporal Volatility Models: An Empirical Study on Financial Network Series

TL;DR

This study empirically compares various spatiotemporal volatility models with different network specifications, demonstrating that certain models, especially the Dynamic Spatiotemporal ARCH, improve out-of-sample forecasting accuracy in financial networks.

Contribution

It provides a comprehensive empirical evaluation of multiple spatiotemporal GARCH models with diverse network structures, highlighting the effectiveness of the Dynamic Spatiotemporal ARCH model.

Findings

Some spatiotemporal models outperform standard GARCH benchmarks.

Dynamic Spatiotemporal ARCH achieves the lowest forecasting errors.

Significant differences confirmed by Diebold-Mariano tests.

Abstract

Various spatiotemporal and network GARCH models have recently been proposed to capture volatility interactions, such as the transmission of market risk across financial networks. These approaches rely heavily on the specification of the adjacency or spatiotemporal weight matrix, for which several alternatives exist in the literature. This paper evaluates the out-of-sample forecasting performance of a range of spatiotemporal volatility models and multivariate GARCH benchmarks under nine alternative network specifications. The empirical analysis uses daily data for 16 sectorally diversified S&P 500 stocks from 22 December 1998 to 20 October 2024. A one-step-ahead forecasting framework is implemented, and models are assessed using BIC, RMSFE, and MAFE, with forecasts evaluated against a single realised volatility proxy based on squared log-returns. The nine spatial weight matrices reflect diverse economic and statistical relationships, including Granger-filtered and EGARCH-based spillovers. Results show that some spatiotemporal models outperform standard GARCH benchmarks in out-of-sample forecasting accuracy. Notably, the Dynamic Spatiotemporal ARCH model achieves the lowest RMSFE and MAFE across all network specifications at minimal computational cost. Pairwise Diebold-Mariano tests confirm significant differences in predictive accuracy. These findings underscore the value of incorporating spatial structure into volatility modelling as a parsimonious and interpretable alternative for financial network analysis.