A1012
Title: Modelling of financial time series with a regime-switching GARCH model including jumps
Authors: Mai Phan - University of Kaiserslautern-Landau & HTW Berlin (Germany) [presenting]
Joern Sass - RPTU Kaiserslautern-Landau (Germany)
Christina Erlwein-Sayer - University of Applied Sciences HTW Berlin (Germany)
Abstract: Time series analysis helps identify underlying patterns and trends in financial data, enabling analysts to make informed predictions about future price movements. Several characteristics of financial time series make this analysis particularly challenging: volatility, non-stationary, heteroscedasticity, non-normal distribution and volatility clusters. Advanced time series models have been developed to address these challenges, such as a regime-switching GARCH model. This model allows for the identification of different regimes or states within financial time series, each with its own distinct volatility structure. By incorporating regime switching, the model can adapt to periods of high and low volatility and captures the dynamic behavior of financial markets. This adaptability makes the regime-switching GARCH model suitable for analyzing highly volatile financial time series like cryptocurrencies. Despite its advantages, the regime-switching GARCH model does not incorporate the occurrence of jumps in financial time series, whose frequencies can vary over time. To address this limitation, a regime-switching GARCH-jump model is proposed. This advanced model includes regime-specific jump frequencies and multiple states, along with GARCH processes tailored to each regime's conditional variance. This combination enhances the model's flexibility in representing the complex behavior of financial markets. This innovative approach is applied to model the daily log returns of Bitcoin.
