Should we trust the Z-score? Evidence from the European Banking Industry

We investigate the accuracy of the Z-score, a widely used proxy of bank soundness, on a sample of European banks from 12 countries over the period 2001-2011. Specifically, we run a horse race analysis between the Z-score and the CAMELS related covariates. Using probit and complementary log-log models, we find that the Z-score's ability to identify distress events, both in the whole period and during the crisis years (2008-2011), is at least as good as the CAMELS variables, but with the advantage of being less data demanding. Finally, the Z-score proves to be more effective when bank business models may be more sophisticated as it is the case for large and commercial banks.