Paper: arXiv 2502.15458

Abstract

Network connections, both across and within markets, are central in countless economic contexts. In recent decades, a large literature has developed and applied flexible methods for measuring network connectedness and its evolution, based on variance decompositions from vector autoregressions (VARs), as in Diebold and Yilmaz (2014). Those VARs are, however, typically identified using full orthogonalization (Sims, 1980), or no orthogonalization (Koop, Pesaran and Potter, 1996; Pesaran and Shin, 1998), which, although useful, are special and extreme cases of a more general framework that we develop in this paper. In particular, we allow network nodes to be connected in ``clusters", such as asset classes, industries, regions, etc., where shocks are orthogonal across clusters (Sims style orthogonalized identification) but correlated within clusters (Koop-Pesaran-Potter-Shin style generalized identification), so that the ordering of network nodes is relevant across clusters but irrelevant within clusters. After developing the clustered connectedness framework, we apply it in a detailed empirical exploration of sixteen country equity markets spanning three global regions.

Complexity vs Empirical Score

  • Math Complexity: 7.5/10
  • Empirical Rigor: 8.0/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper introduces a sophisticated clustered VAR framework with extensive LaTeX derivations for impulse response and variance decomposition identification (high math). It then applies this framework in a detailed empirical study of 16 global equity markets using standard econometric software and likely extensive data processing, demonstrating backtest-ready implementation (high rigor).

Research Flowchart

  flowchart TD
  A["Research Goal<br>Develop & apply new framework<br>for measuring network connectedness"] --> B["Methodology Development<br>Clustered Connectedness Framework"]
  
  B --> C["Data/Inputs<br>16 Country Equity Markets<br>3 Global Regions"]
  
  C --> D["Computational Process<br>1. Estimate VAR models<br>2. Apply Clustered Identification<br>3. Calculate Variance Decompositions"]
  
  D --> E["Key Findings/Outcomes<br>1. Framework allows<br>intra-cluster correlation<br>2. Inter-cluster orthogonality<br>3. Ordering irrelevant within clusters<br>4. Superior network measurement<br>5. Application to global equity markets"]
  
  style A fill:#e1f5fe
  style B fill:#f3e5f5
  style C fill:#e8f5e8
  style D fill:#fff3e0
  style E fill:#fce4ec

Cited References (36)

  1. Local Projections (2024) — link
  2. Cluster GARCH — → 2406.06860
  3. Genuinely Robust Inference for Clustered Data (2023) — link
  4. Incorporating Prior Knowledge of Latent Group Structure in Panel Data Models (2022) — link
  5. On the Past, Present, and Future of the Diebold-Yilmaz Approach to Dynamic Network Connectedness (2022) — link
  6. Cluster-robust inference: A guide to empirical practice (2022) — link
  7. Detecting groups in large vector autoregressions (2021) — link
  8. Community Detection in Partial Correlation Network Models (2020) — link
and 28 more
  1. Local Projection Inference Is Simpler and More Robust Than You Think (2020) — link
  2. When do common time series estimands have nonparametric causal meaning? (2019) — link
  3. Network vector autoregression (2017) — link
  4. Discretizing Unobserved Heterogeneity (2017) — link
  5. Grouped Patterns of Heterogeneity in Panel Data (2015) — link
  6. ForceAtlas2, a Continuous Graph Layout Algorithm for Handy Network Visualization Designed for the Gephi Software (2014) — link
  7. The Financial Crisis of 2007-2009 (2012) — link
  8. ON THE ADAPTIVE ELASTIC-NET WITH A DIVERGING NUMBER OF PARAMETERS (2009) — link
  9. Measuring Financial Asset Return and Volatility Spillovers, with Application to Global Equity Markets* (2008) — link
  10. A Comprehensive Look at the Empirical Performance ofEquity Premium Prediction II (2008) — link
  11. Implications of Dynamic Factor Models for VAR Analysis (2005) — link
  12. Estimation and Inference of Impulse Responses by Local Projections (2005) — link
  13. No Contagion, Only Interdependence: Measuring Stock Market Comovements (2002) — link
  14. Impulse response analysis in nonlinear multivariate models (1996) — link
  15. MACROECONOMICS AND REALITY (1977) — link
  16. Estimation of Grouped Time-Varying Network Vector Autoregression Models (2024) — link
  17. Improved methods for detecting sender/receiver clusters (2022)
  18. Conditions under which IRFs and VDs may be given causal interpretation, and how those conditions relate to connectedness of the associated network (2021)
  19. The connectedness measurement potential of VDs obtained not via traditional VAR IRFs, but rather via local projection IRFs (2021)
  20. The onset of the COVID-19 pandemic in (2020)
  21. Estimating Global Bank Network Connectedness (2017) — link
  22. On the network topology of variance decompositions: measuring the connectedness of financial firms (2014)
  23. Better to give than to receive: Predictive directional measurement of volatility spillovers (2012) — link
  24. Generalized Impulse Response Analysis in Linear Multivariate Models (1998) — link
  25. Regression Shrinkage and Selection via the Lasso (1996) — link
  26. for improved anticipation and tracking of cross-market spillover episodes as,
  27. Others who may not be directly involved in financial markets, but who may want to use the markets to help assess the effects of non-financial policies
  28. The effects of cluster mis-classification

1 of 36 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.