Abstract

Vctor Auto-regression Model (VAR) has recently become a popular tool for economic analysis and forecasting for multivariate co-integrated time series. In the context of globalization, through a growing process of economic integration among countries and financial markets, the interdependency among major world financial markets is more than evident The paper covers the After Global crises period 2009-2013 using weekly based data and investigates and examines the short and long-run relationships between major world financial markets with particular attention to the Greek stock exchange. The research methodology employed includes testing for stationary, both with the Dickey- Fuller and the Phillips-Perron tests, the use of a VAR (Proc VARMAX) In SAS® model for the implementation of the Granger Causality test, and Co-integration tests according to Johansen-Juselious. The results confirm the dominance of the USA financial market and the strong influence of DAX and FTSE on all other markets of the sample. The influence of Germany and the DJ index is especially noticeable on the Athens stock exchange. We conduct co-integration tests with variance decomposition and estimate the impulse response functions. This paper demonstrates these techniques using SAS®/ETS 9.22 forecasting software. The comparison generated from the program helps us to decide the best forecasting method.

Key Word: Market Interdependency, Variance decomposition, VAR Model, Visual analytics