In the paper the issue of PD (probability of default) rating model calibration and of its presentation in the general context of economic model calibration is discussed. The rating model in the credit risk area is defined and two approaches for its calibration to a masterscale are presented and applied for empirical data. The first approach uses the reversed regression method while the second is based on reversing the estimated link function. Two possible link functions reported by the literature are used and discussed..
Financed by the National Centre for Research and Development under grant No. SP/I/1/77065/10 by the strategic scientific research and experimental development program:
SYNAT - “Interdisciplinary System for Interactive Scientific and Scientific-Technical Information”.