Preliminary Test for Stationary of the Time Series
A particular time series is said to be stationary or non-stationary by using a Unit Root
Test, before proceeding to the identification of a possible long run relationship, it is necessary to
verify that all variables are integrated of order one in levels. To test the time series in this study
over the period 1974-2012, a Unit Root Test has been performed, the test applied is well known
Augmented Dickey-Fuller test (ADF).
All variables are tested both in levels and first difference with a constant and a constant
with a time trend. The results show that the unit-root hypothesis cannot be rejected when the
variables are taken in levels. However, when the first differences are used, the hypothesis of unit
root non-stationary is rejected at the 1% level of difference. These results lead us to conclude that
our series are characterized as an I(1) process, Unit Root Test results are reported in Table (1).
Do'stlaringiz bilan baham: |