This article uses a Value‐at‐Risk approach to derive an estimator of the failure probability of a financial institution. The proposed approach can be applied to any profit/loss distribution, although Extreme Value (EV) theory also tells us that the most appropriate distributions are EV. The estimator suggested here is superior to the “Z” indicator of failure risk, which is sometimes used in the literature. Illustrative results confirm that the distribution selected makes a considerable difference to the results, and that estimates of failure probabilities based on the assumption of normality are too low to be valid.
CitationDownload as .RIS
MCB UP Ltd
Copyright © 2001, MCB UP Limited