Use this URL to cite or link to this record in EThOS: http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.528505
Title: Generalized vasicek credit loss distributions under non-gaussianity
Author: Zuk, Enrique Eugenio Batiz
Awarding Body: The University of Manchester
Current Institution: University of Manchester
Date of Award: 2010
Availability of Full Text:
Access from EThOS:
Abstract:
The objective of this thesis is to investigate various extensions to Vasicek's (1987, 2002) regulatory Gaussian credit risk model for improving current credit risk management practices. The thesis first provides a comprehensive review of Vasicek's (1987, 2002) Gaussian structural model for the distribution of credit portfolio losses, its theoretical extensions and the empirical applications in the literature. This is followed by four empirical studies. My first empirical study examines the impact of skewness and excess kurtosis of the asset return process on the shape of the credit loss distribution and, consequently, over the Basel II requirements. My second empirical study investigates the combined impact of contagion across economic sectors and a non-Gaussian common factor on the shape of the credit loss distribution. My third empirical study contains a Monte Carlo study of the robustness of the probability of default and asset correlation estimators of the Basel II Gaussian model when the true loss data generating process follows a non-Gaussian asset return process. Finally, I investigate the accuracy of the correlation parameter prescribed in Basel II for US and Mexico
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID: uk.bl.ethos.528505  DOI: Not available
Share: