Validation of rating models calibration

Often internal rating systems do not fully satisfy standard calibration tests used for PD validation. According to the document “Studies on validation of internal rating systems” issued by the Basel Committee on Banking Supervision (WP n. 14, May 2005), still a milestone on this topic, “correct calibration of a rating system means that the PD estimates are accurate. Hence, for examining calibration somehow the differences of forecast PDs and realised default rates must be considered. This can be done simultaneously for all rating grades in a joint test or separately for each rating grade, depending on whether an overall assessment or an in detail examination is intended”.2 Many reasons could lead to fail calibration tests even by otherwise well performing rating systems. Two reasons are particularly critical: rating philosophy (TTC versus PIT ratings) and default correlation.