Bank failure intensity modeling: an ACD model approach. Issue 5 (19th November 2018)

• Record Type: Journal Article
• Authors: Siakoulis, Vasileios
• Is Part Of: Journal of risk finance. Volume 19:Issue 5(2018)
• Page Start: 454
• Page End: 477
• Publication Date: 2018-11-19
• Subjects: Structural breaks -- Financial contagion -- Autoregressive conditional duration -- Bank failures -- Economic environment; C22 -- C41 -- G01 -- G12 -- G14; Risk management -- Periodicals; Risk (Insurance) -- Periodicals; Risk assessment -- Periodicals; 658.155
• DOI: 10.1108/JRF-11-2016-0151
• Languages: English
• ISSNs: 1526-5943

Abstract

Abstract : Purpose: The purpose of this study is to employ a duration-based approach to model the inter-arrival times of bank failures in the US banking system for the period of 1934-2014, in line with the suggestions ofFocardi and Fabozzi (2005 ), who used a similar model for explaining contagion in credit portfolios. Design/methodology/approach: Conditional duration models that allow duration between bank failures to depend linearly or nonlinearly on its past history are estimated and evaluated. Findings: The authors find evidence of strong persistence along with nonmonotonic hazard rates, which imply a financial contagion pattern, according to which a high frequency of bank failures generates turbulence, which shortly after leads to additional fails, whereas prolonged periods without abnormal events signify the absence of contagious dependence, which increases the relative periods between bank failure appearance. Further, the authors obtain statistically significant results when they allow duration to depend linearly on past information variables that capture systemic bank crisis factors along with stock and bond market effects. Originality/value: The originality of this study consists in proposing a new time series approach for the prediction of bank probability of default by incorporating a default-risk contagion mechanism. As contagious bank failures are a key topic in macroprudential supervision, this study could be of value for supervisory authorities in setting pro-active actions and tightening regulatory measures.