Risk measurement for portfolio credit risk based on a mixed Poisson model (Q2321449)

Summary: Experiences manifest the importance of comovement and communicable characters among the risks of financial assets. Therefore, the portfolio view considering dependence relationship among credit entities is at the heart of risk measurement. This paper introduces a mixed Poisson model assuming default probabilities of obligors depending on a set of common economic factors to construct the dependence structure of obligors. Further, we apply mixed Poisson model into an empirical study with data of four industry portfolios in the financial market of China. In the process of model construction, the classical structural approach and option pricing formula contribute to estimate dynamic default probabilities of single obligor, which helps to obtain the dynamic Poisson intensities under the model assumption. Finally, given the values of coefficients in this model calculated by a nonlinear estimation, Monte Carlo technique simulates the progress of loss occurrence. Relationship between default probability and loss level reflected through the MC simulation has practical features. This study illustrates the practical value and effectiveness of mixed Poisson model in risk measurement for credit portfolio.