Testing Granger causality with application to Exchange rates for Swedish kronor with GB pound and US dollar

Abstract: This thesis undertakes the Causality study with application to exchange rates for Swedish kronor (SEK) with GB pound (£) and US dollar ($) in the frame work of vector Autoregressive (VAR) model. We present the theory behind the Granger Causality, unit roots and vector auto-regression. The Augmented Dickey-Fuller test for unit roots is performed. Our data consist of three time series of daily foreign exchange rates, starting from 23rd November, 2007 to 21st May, 2008. Granger causality is a technique for determining whether one time series is useful in forecasting another. By applying this technique, we try to observe the casual relationship which exists between the three currencies of our study.