Cross-Country Assessment of Systemic Risk in the European Stock Market: Evidence from a CoVaR Analysis

Abstract

This work is intended to assess the contribution to systemic risk of major companies in the European stock market on a geographical basis. We use the EuroStoxx 50 Index as a proxy for the financial system and we rely on the CoVaR and -CoVaR risk measures to estimate the contribution of each European country belonging to the index to systemic risk. We also conduct the significance and dominance test to evaluate whether the systemic relevance of considered countries is statistically significant and to determine which nation exerts the greatest influence on the spreading of negative spillover effects on the entire economy. Our empirical results show that, for the period ranging from 2008 to 2017, all countries contribute significantly to systemic risk, especially in times of crisis and high volatility in the markets. Moreover, it emerges that France is the systemically riskiest country, followed by Germany, Italy, Spain and Netherlands.

COVID-19 Shock and the Time-Varying Volatility Spillovers Among the Energy and Precious Metals Markets: Evidence From A DCC-GARCH-CONNECTEDNESS Approach

“…This finding confirms the conclusion of the static analysis and is consistent with the conclusions of Benlagha and Omari (47) and Farid et al (35). The main reason may relate to the sentiment of the investors in markets (12,48), which will amplify the negative impact of the COVID-19 epidemic shock. Additionally, Figure 2 depicts that the impacts of the COVID-19 epidemic on the energy and precious metals markets had clear time-varying characteristics.…”

Joint estimation of conditional quantiles in multivariate linear regression models with an application to financial distress

“…Then, using (42), the complete log-likelihood function (up to additive constant terms) can be written as follows:…”

“…Using the joint distribution of Y and W derived in (42) and the pdf of Y given in (10), we have that…”

“…In fact, unlike standard linear regression models, which only consider the conditional mean of a response variable, quantile regression allows one to assume that the relationship between the response and explanatory variables can vary across the conditional distribution of the dependent variable. Many univariate quantile regression methods are now well consolidated in the literature and have been implemented in a wide range of different fields, like medicine (see e.g., Cole and Green (1992) and Royston and Altman (1994), Marino et al (2016)), survival analysis (Koenker and Geling (2001)), financial and economic research (Bassett and Chen (2001), Hendricks and Koenker (1992), Petrella et al(2017)), and environmental modelling (see Pandey and Nguyen (1999) and Hendricks and Koenker (1992) for a discussion). Koenker (2005) provides an overview of the most used quantile regression techniques in a classical setting.…”

A two-part finite mixture quantile regression model for semi-continuous longitudinal data

“…Quantile regression methods have become widely used in literature mainly because they are suitable in all those situations where skewness, fat-tails, outliers, truncation, censoring and heteroscedasticity arise. They have been implemented in a wide range of different fields, both in a frequentist paradigm and in a Bayesian setting, spanning from medicine (see Cole and Green (1992); Royston and Altman (1994); Alhamzawi et al (2012) and Waldmann (2018)), financial and economic research (see Bassett and Chen (2002); Bernardi et al (2015); Petrella et al (2018); Laporta et al (2018); Tian et al (2018); Bernardi et al (2018) and Petrella and Raponi (2019)) and environmental modeling; see, e.g., Hendricks and Koenker (1992); Pandey and Nguyen (1999) and Reich et al (2011) for a discussion. For a detailed review and list of references, Koenker (2005) and Koenker et al (2017) provide an overview of the most used quantile regression techniques in a classical setting.…”