In this paper a Bayesian Markov chain Monte Carlo (MCMC) method discussed in Huang and Yu (2010) is applied to estimate the credit risk models with microstructure noise, using the daily equity data from China. In literature, the observed equity prices are known to be influenced by market microstructure effects so that they deviate from the corresponding efficient prices. Credit risk models with microstructure noise is a way to depict this relationship. In the Bayesian framework, we employ Gibbs sampling, which is a Markov chain Monte Carlo (MCMC) technique, to analyze such models. We estimate the model with Gaussian iid microstructure term, using equity data of the firms in the Shanghai Stock Exchange 50 index constitutes. Estimates in the model converge well when we use the data of 6 firms out of 16 in our sample.
credit risk, bayesian MCMC, microstructure noise, default probability
MSc in Economics
Econometrics | Finance | Statistical Models
Structural Credit Risk Models with Microstructure Noise: An Empirical Analysis for China. (2011). Dissertations and Theses Collection (SMU Access Only).
Available at: http://ink.library.smu.edu.sg/etd_coll_smu/15
Copyright Owner and License
Room 5016, School of Economics, Singapore Management University, 90 Stamford Road, Singapore 178903