Forecasting Volatility Spillovers Using Advanced GARCH Models: Empirical Evidence for Developed Stock Markets from Austria and USA

Abstract

The research study voyage commences with the foundational objective of fitting a suitable Generalized Autoregressive Conditional Heteroscedastic (GARCH) model to assess market volatility, a fundamental pillar of financial analysis. This research embarks on an ambitious quest to predict and understand stock market volatility within the realms of the DJIA and S&P 500 of USA and ATX index of Austria using different sophisticated GARCH models. The dataset used in this study comprises daily stock market data for two key indices: the S&P 500 Index, representing the USA stock market, and the ATX Index, representing the Austria stock market. Additionally, the DJIA Index, another representative of the USA stock market, was included. The dataset consists of 5967 daily observations over the specified time period from January 3, 2000, to September 21, 2023. The observation of results, analysis and discussion depicts that PARCH model shows most promising results and found suitable to model the volatility patterns of the selected indices. The findings and methodologies presented in this paper can be seen as a solid foundation upon which to build future investigations, refining our ability to anticipate market movements and make informed decisions in an uncertain financial landscape. In closing, this research not only contributes to the body of knowledge in financial econometrics but also underscores the importance of modeling long-term stock market behavior with precision and diligence.

Keywords

• volatility patterns
• garch family models
• volatility forecasting
• stock market
• financial analysis