Measuring systemic financial risk and analyzing influential factors: an extreme value approach

Abstract

Purpose – The purpose of this paper is to measure a single financial institution's contribution to systemic risk by using extremal quantile regression and analyzing the influential factors of systemic risk. Design/methodology/approach – Extreme value theory is applied when measuring the systemic risk of financial institutions. Extremal quantile regression, where extreme value distribution is assumed for the tail, is used to measure the extreme risk and analyze the changes in and dependencies of risk. Furthermore, influential factors of systemic risk are analyzed using panel regression. Findings – The key findings of the paper are that value at risk and contribution to systemic risk are very different when measuring the risk of a financial institution; banks’ contributions to systemic risk are much higher; and size and leverage ratio are two significant and important factors influencing an institution's systemic risk. Practical implications – Characterizing variables of financial institutions such as size, leverage ratio and market beta should be considered together when regulating and constraining financial institutions. Originality/value – To take extreme risk into account, this paper measures systemic financial risk using extremal quantile regression for the first time.