3.4 Estimation
techniques
This study employs the ADF and Johansen as a test of
stationality, cointegration test and modeling. They are all adopted in order
to arrive at a conclusion that will be free from any doubt and this can lead to
the acceptance of conclusions and recommendations of the present research.
3.4.1 Unit Root Test
Consider the model:
The Stationarity condition is |ö| < 1. In general we
have three possible cases.
|ö| < 1 and therefore the series are stationary.
|ö| > 1where in this case the series explodes.
ö = 1 where in this case the series contains a unit root
and is non-stationary.
For testing that is there any unit roots in the series the
Augmented Dickey-Fuller test for unit roots will be used.
The Augmented Dickey Fuller (ADF) test will be employed as a
prior diagnostic test before the estimation of the model to examine the
stochastic time series process properties of monetary policy and Consumer price
index. This enables us to avoid the problems of spurious result that
are associated with non-stationary time series models.
3.4.2 Co-integration Test
This is employed to determine the number of
co-integrating vectors methodology with two different test statistics
namely the Trace test statistic and the Maximum Eigen-value test
statistic.
| 
