Portfolio Credit Risk Estimation under the Dynamic Factor Model

Chih-Tun Yu ； Hui-Mei Liu ； Ming-Chin Hung

《中國統計學報》 49卷4期 (2011/12) Pp. 123-139

https://doi.org/10.29973/JCSA.201112.0001

並列摘要

Under the Basel II accord, a single factor model characterizes the regulatory capital calculations and the portfolio credit risk of the internal ratings based approach. However, this model assumes independent and identically distributed common factor which may produce inaccurate estimates of default probabilities and asset correlation. In this paper, we address a dynamic factor model to improve this phenomenon. This model can capture both dynamic behavior of default risk and dependence among individual obligors. We use a Monte Carlo Expectation Maximization (MCEM) algorithm along with a Gibbs sampler and an acceptance methods when estimating the unknown parameters. Moreover, the empirical study using the default data from the Standard and Poor's shows evidence of profound serial dependence of the default rate in the Standard and Poor's data.

並列關鍵字

Monte Carlo Expectation Maximization algorithm ； default probability ； asset correlation ； dynamic factor model

參考文獻

Basel Committee on Banking Supervision(2004).Basel II: Intemational Convergence of Captal Measurement and Capital Standards: A Revised Framework.Bank for International Settlements.

Basel Committee on Banking Supervision(2006).Basel II: International Convergence of Capital Measurement and Capital Standards: A Revised Framework-Comprehensive Version.Bank for International Settlements.

Bluhm, C.,Overbeck, L.,Wagner, C.(2002).An Introdu ction to Credit Risk Modeling.New York:Chapman & Hall.

Dempster, A. P.,Laird, N. M.,Rubin, D.(1977).Maximum likelihood from incomplete data via the EM algorithm.Journal of the Royal Statistical SocietyB.39,1-38.

Durbin, J.,Koopman, S. J.(1997).Monte Carlo maximum likelihood estimation for non-Gaussian state space models.Biometrika.84,669-684.