ARMA-GARCH Model and temporal precedence between stock indices

Abstract

Faced with the need for risk valuation of financial assets, investors demand sophisticated methods of modeling that can judge the variability of their investments. At the same time, financial globalization has been characterized by common movements and trends between different international markets. In this context, the main objective of this paper was to model the statistical volatility of the Bovespa Index (Ibovespa) and the Dow Jones Industrial Average Index, using ARMA-GARCH adjustments, in addition to checking the existence of a long- -term balance and temporal precedence between these variables, using the Johansen co-integration and Granger causality tests, respectively. The results established a higher heterogeneous variance for Ibovespa and the existence of temporal precedence for the Dow Jones Index, despite the absence of any long-term balance between the series. It is understood that the latter behavior may have been caused by the existing difference between the conditional heteroscedasticity of each index.

Keywords

• Conditional heteroscedasticity
• Co-integration
• . Causality
• Stock indices.