Activity Number:
|
621
- Portfolio Choice, Stock Returns, Bankrupcty, and Default
|
Type:
|
Contributed
|
Date/Time:
|
Thursday, August 3, 2017 : 8:30 AM to 10:20 AM
|
Sponsor:
|
Business and Economic Statistics Section
|
Abstract #324332
|
View Presentation
|
Title:
|
Bayesian Estimation of the Default Rate Distributions with Non-Gaussian Single Factor Models
|
Author(s):
|
Takayuki Shiohama*
|
Companies:
|
Tokyo University of Science
|
Keywords:
|
default rate distribution ;
particle filter ;
Bayesian estimation ;
credit portfolio risk ;
state-space model
|
Abstract:
|
We consider a state-space model for the default rate distribution of Vasicek's single factor models with portfolio credit losses. The proposed default rate distributions incorporate with non-Gaussian distributions in the asset returns together with the time-varying parameters for the probability of default (PD) and the asset correlation among the obligors. Simulation-based inference using sequential Monte Carlo methods for computing the posterior distributions for the state variables and unknown parameters are investigated. By comparing the estimated model parameters with time-varying credit portfolio risks with an ordinary method, this approach provides useful insight for the appropriate evaluation for the credit portfolio risks.
|
Authors who are presenting talks have a * after their name.