AN IMPROVEMENT FORECAST USING VECTOR AUTOREGRESSION APPROACH ON TAX REVENUE IN NIGERIA

Baba Gimba Alhassan and Nma Musa Tela 

Department of Statistics,

The Federal Polytechnic, Bida, Niger State

Email: gazhigun@gmail.com  

ABSTRACT 

The paper proposed an improved Multivariate time series model for tax revenue using Vector Auto regression (VAR) approach. The advantage of this study is to verify the error variance decomposition on both the transformed and un-transformed data. To check the efficiency this, approach the four stages of VAR were observed with R package to examine the MAE, RMSE, MAPE, and MSE. The result shows that, the error variance decomposition in transformed data is less than the error variance decomposition in Untransformed data (i.e 1.5e-15 < 2.2e-16) which means that, there’s significant difference in the error variance decomposition  The models suggested by information criterion procedure are different because VAR (1) model is selected for transformed data for all the criterions while  by information criterion procedures, however VAR (3) model is the most suitable model for the data sets based on the model adequacy checking and accuracy testing.