The Credibility Theory applied to backtesting Counterparty Credit Risk

Abstract

Credibility theory provides tools to obtain better estimates by combining individual data with sample information. We apply the Credibility theory to a Uniform distribution that is used in testing the reliability of forecasting an interest rate for long term horizons. Such empirical exercise is asked by Regulators (CRR, 2013) in validating an Internal Model Method for Counterparty Credit Risk. The main results is that risk managers consider more reliable the output of a test with limited sample size when the Credibility is applied to define a confidence interval.