Open AccessModeling stock market volatility in Croatia
Author(s) -
Hrvoje Jošić,
Berislav Žmuk
Publication year - 2021
Publication title -
ekonomski vjesnik
Language(s) - English
Resource type - Journals
eISSN - 1847-2206
pISSN - 0353-359X
DOI - 10.51680/ev.34.2.14
Subject(s) - autoregressive conditional heteroskedasticity , stock market index , econometrics , volatility (finance) , stock market , economics , stock (firearms) , stock exchange , financial economics , index (typography) , geography , finance , computer science , context (archaeology) , archaeology , world wide web
Purpose: In this paper, the volatility of the Croatian stock market index CROBEX is investigated using the GARCH(1,1) model. Methodology: The novelty provided by this paper is the estimation of the GARCH(1,1) model by using three conditional error distributions (normal (Gaussian) distribution, Student’s-distribution with fixed degrees of freedom and generalized error distribution (GED) with fixed parameters). Results: The findings obtained in the research are in the line with previous research in this field (Erjavec & Cota, 2007; Sajter & Ćorić, 2009). The volatility of CROBEX returns is positively correlated with the volume of trade on the Zagreb Stock Exchange and movements on the main European and American stock markets. The movement of S&P 500 stock market index returns is transmitted from the previous day, providing signals for the direction of change of CROBEX index returns in the present. Conclusion: Therefore, this paper provides evidence that investors in Croatia strongly rely on the past information received from the American S&P500 stock market index. Furthermore, there seems to exist theco-movement between CROBEX and main European indexes on the same trading day.