Comment on the Variance in the Paper Entitled ‘Credit Risk Measures and the Estimation Error in the ASRF Model Under the Basel II IRB Approach’ by Simone Casellina, Simone Landini, and Mariacristina Uberti
You can manage bookmarks using lists, please log in to your user account for this.
Media type:
E-Book
Title:
Comment on the Variance in the Paper Entitled ‘Credit Risk Measures and the Estimation Error in the ASRF Model Under the Basel II IRB Approach’ by Simone Casellina, Simone Landini, and Mariacristina Uberti
Footnote:
Nach Informationen von SSRN wurde die ursprüngliche Fassung des Dokuments August 1, 2023 erstellt
Description:
The European banking regulation does neither specify a methodology nor a level of confidence for the purpose of quantifying the margin of conservatism for the general estimation error (MoC C) of risk parameter estimates. In order to fill this gap, Casellina et al. (2023) determine the MoC C of probability of default estimates based on the upper endpoint of a confidence interval of the long run average default rate (LRADR). In doing so, the authors assume an infinite granular portfolio. Consequently, their level of MoC C does not increase with decreasing number of observations contrary to European banking supervisors’ expectation. Therefore, we derive step-by-step an upper bound / equation for the variance of the LRADR, which is a (strictly) monotonically decreasing function of the number of obligors. Replacing equation (11) of Casellina et al. (2023) with this upper bound / equation thus improves compliance with expectations of European banking supervisors