Quantile methods for complex financial systems

• Applicants: Professorin Dr. Melanie Schienle; Professorin Dr. Weining Wang
• Subject Area: Statistics and Econometrics
• Term: from 2016 to 2020
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 290808748

• Final Report Year: 2024

Final Report Abstract

Financial systems have become increasingly complex. They are characterized by their large dimensional, strong cross-sectional dependence amounting to networks of unknown and timevarying form which appear as main drivers of risk of and within the system. Moreover, in turbulent market times, accurate estimation and prediction of systemic and idiosyncratic risk requires novel econometric and statistical models and techniques that account for the network topology but also for macro- and micro-economic factors and determinants in order to quickly adjust and respond to changing environments. In this project, we provide innovative techniques to better estimate and predict moderate and extreme risk in complex systems. This is of key interest for financial market participants and for prudential supervisors, but also delivers solutions for a better understanding of other complex systems such as electricity markets. We focus on econometric methodologies for conditional quantiles directly related to the Value-at-Risk (VaR) concept for risk measurement. Though, all presented approaches are readily extendible to further risk measures such as expected shortfall or others. In particular, we have developed statistical concepts for (tail) networks uncovering novel structural risk channels within large dimensional financial systems and for determining suitable tail factors for accurate prediction. Beyond that, we have developed novel techniques that address further challenges in dynamic networks such as their dynamic evolution, high-dimensionality, nonstationarity and causal effect identification. For the general public, we have graphically illustrated and maintained the practical impact on financial systemic risk measurement of many of our techniques on the companion website.

Link to the final report

https://hdl.handle.net/10419/317989

Publications

• Beyond Dimension two: A Test for Higher-Order Tail Risk. Journal of Financial Econometrics, 14(3), 552-580.
  Bormann, Carsten; Schaumburg, Julia & Schienle, Melanie
  
• TENET: Tail-Event driven NETwork risk. Journal of Econometrics, 192(2), 499-513.
  Härdle, Wolfgang Karl; Wang, Weining & Yu, Lining
  
• Single-Index-Based CoVaR With Very High-Dimensional Covariates. Journal of Business & Economic Statistics, 36(2), 212-226.
  Fan, Yan; Härdle, Wolfgang Karl; Wang, Weining & Zhu, Lixing
  
• Detecting Structural Differences in Tail Dependence of Financial Time Series. Journal of Business & Economic Statistics, 38(2), 380-392.
  Bormann, Carsten & Schienle, Melanie
  
• Determination of vector error correction models in high dimensions. Journal of Econometrics, 208(2), 418-441.
  Liang, Chong & Schienle, Melanie
  
• Network quantile autoregression. Journal of Econometrics, 212(1), 345-358.
  Zhu, Xuening; Wang, Weining; Wang, Hansheng & Härdle, Wolfgang Karl
  
• LASSO-driven inference in time and space. The Annals of Statistics, 49(3).
  Chernozhukov, Victor; Karl, Härdle Wolfgang; Huang, Chen & Wang, Weining
  
• Assessing the impact of policy and regulation interventions in European sovereign credit risk networks: What worked best?. Journal of International Economics, 139, 103673.
  Buse, Rebekka; Schienle, Melanie & Urban, Jörg
  
• Dynamic Network Quantile Regression Model. Journal of Business & Economic Statistics, 42(2), 407-421.
  Xu, Xiu; Wang, Weining; Shin, Yongcheol & Zheng, Chaowen
  
• Large Spillover Networks of Nonstationary Systems. Journal of Business & Economic Statistics, 42(2), 422-436.
  Chen, Shi & Schienle, Melanie