Bank Insolvency Risk and Z-Score Measures: Caveats and Best Practice
Authors:
- Vincent BouvatierVBVincent Bouvatier
- Laetitia LepetitLLLaetitia Lepetit
- Pierre Nicolas RehaultPRPierre Nicolas Rehault
- Frank StrobelFSFrank Strobel
Preprint
- 1 January 2017
- preprint
- Published by Elsevier in SSRN Electronic Journal
Abstract
We evaluate several alternative approaches to the construction of time-varying Z-scores as bank insolvency risk measures. Focusing on US and European banks during the financial crisis of 2007-2008, we carry out comparisons of the different measures considered using a range of alternative testing procedures. For both US and European data, Z-scores computed with the exponentially weighted moments method are shown to be preferable to those computed with the more commonly used moving moments approach. Generally, or if only simple moving moments are used, Z-scores computed with current values of the capital-asset ratio are recommended.Keywords
All Related Versions
This publication has 26 references indexed in Scilit:
- Institutional development and bank stability: Evidence from transition countriesJournal of Banking & Finance, 2014
- Bank insolvency risk and time-varying Z-score measuresJournal of International Financial Markets, Institutions and Money, 2013
- Nontraditional banking activities and bank failures during the financial crisisJournal of Financial Intermediation, 2013
- Bank competition and stability: Cross-country heterogeneityJournal of Financial Intermediation, 2013
- The banking bailout of the subprime crisis: Was the bang worth the buck?Journal of International Financial Markets, Institutions and Money, 2013
- Assessing the Performance of Classification MethodsInternational Statistical Review, 2012
- Coefficients of Determination in Logistic Regression Models—A New Proposal: The Coefficient of DiscriminationThe American Statistician, 2009
- Measuring classifier performance: a coherent alternative to the area under the ROC curveMachine Learning, 2009
- Likelihood Ratio Tests for Model Selection and Non-Nested HypothesesEconometrica, 1989
- Updating mean and variance estimatesCommunications of the ACM, 1979