Richard Luger, Université Laval - Multiple Testing for the Topology of Financial Networks

Title:   Multiple Testing for the Topology of Financial Networks

Abstract: This paper advances the econometric analysis of network connectedness by introducing exact simulation-based inference methods to assess pairwise and aggregated spillover effects among variables in vector autoregressive models. While the estimation of connectedness using forecast error variance decompositions is well established, our contribution lies in developing hypothesis testing procedures that provide a statistical foundation for assessing the significance of connectedness measures. To address the resulting multiple testing problem, we present algorithms for both single-step and step-down p-value adjustments that control the familywise error rate in finite samples. We also extend the methodology to group-based analysis, thereby broadening its applicability. Simulation results show that our procedures ensure simultaneous finite-sample correctness while maintaining good statistical power. We illustrate the proposed inference procedures through empirical analyses of return and volatility spillovers among global stock markets, revealing new insights into financial market linkages and the vulnerability of financial networks to contagion.

Presenter: Richard Luger, Université Laval

If you would like to subscribe to the Melbourne Institute Seminar Series email list, please contact us.