The role of volatility persistence in default probability prediction: A Bayesian model.

This thesis studies the significance of lagged value of stochastic volatility process in the prediction of probability of default in one year, and in estimation of credit default swap spreads. The novelty of the model consists in allowing for both stochastic interest rate and volatility and in the extension of the dynamics of SV process to AR (2) process. The estimation is carried out by exploiting Bayesian methods via implementation of Gibbs sampling for the state space model of stochastic volatility and returns and Metropolis Hastings acceptance rejection sampling algorithms. The model is compared with Merton’s basic SCR model and with the SCR model with stochastic interest rate presented in Rodriguez et al (2014) on the basis of marginal likelihoods, using financial data series of three firms .