Extreme Value Modelling of Ghanaian Commercial Banks

Extreme event modeling has always attracted attention in domains such as hydrology, as well as in major financial markets where modelers benefit from an abundance of available data (Embrechts et. al, 1997). Following the recent global financial crises, however, proper models for modeling such unusual events that lead to crises have become critical in the finance and risk management disciplines. This work uses extreme value theory (EVT) to fit a model to the tails of the daily stock returns data to model the extreme values of a listed commercial bank on the Ghana stock exchange, specifically Access Bank (2007–2019). An ARMA-GARCH model was fitted to the data to correct for the effects of autocorrelation and conditional heteroscedastic terms present in the returns series before the EVT method was applied. The Peaks over Threshold technique was used for estimation, which involves fitting a Generalized Pareto Distribution (GPD) model to excesses above a predetermined threshold. The results show that the GPD provides an adequate fit to the surplus data