Sprekers /Presenters : Dr Mesias Alfeus (SU/Statistics and Actuarial Science)
Titel/Title : Stochastic default risk estimation: Evidence from the South African financial market
Tyd/Time : 13:00 – 14:00, Friday 8th of September 2023
Plek/Location : MS Teams and VDS 3022
The present paper provides empirical studies to estimate defaultable bonds in the South African financial market. The main goal is to estimate the unobservable factors affecting bond yields for South African major banks. The maximum likelihood approach and a global optimisation based on Adaptive Simulated annealing (ASA) are adopted for the estimation methodology. Extended Kalman filtering techniques are employed to tackle the situation that the factors cannot be observed directly. Multi-dimensional Cox-Ingersoll-Ross (CIR)-type factor models are considered. Results show that default risk increased sharply in the South African financial market during COVID-19 and the CIR model with jumps exhibits a better performance.
Joint work with Kirsty Fitzhenry and Alessia Lederer