Credit Rating Dynamics in the Presence of Structural Breaks

• Activity Number: 174
• Type: Contributed
• Date/Time: Monday, August 2, 2010 : 10:30 AM to 12:20 PM
• Sponsor: Business and Economic Statistics Section
• Author(s): Haipeng Xing and Ning Sun*+ and Ying Chen
• Companies: State University of New York at Stony Brook and State University of New York at Stony Brook and MEAG New York
• Keywords: Credit transitions ; Hidden Markov models ; Structural Breaks

Abstract

Credit transition matrices are typically modeled as a Markov process with constant transition probability or generator matrix. Based on empirical evidence, we propose a stochastic structural break model for piecewise constant rating transition matrices with unknown number, locations and magnitude of structural breaks. The proposed model provides explicit forms for the posterior distribution of the time-varying rating transition probability matrices that are mixtures of Markov chains. The model also allows us to make inference on the probability of structural break at each period and prediction of transition matrices in the presence of possible structural break. We estimate this model using credit rating histories and show that the proposed model captures indeed the structural break in credit rating transitions.