THE FITTING OF ARIMA MODEL IN FORECASTING NIGERIA

GROSS DOMESTIC PRODUCT (GDP)

¹Amadi, Innocent Uchenna and ²Aboko, Simon Igboye

¹Department of Mathematics/Computer Science, Rivers State University of Science and Technology, Oroworukwo, Nigeria

²Department of Mathematics/Statistics, Rivers State College of Arts and Science Rumuola, Nigeria.

E-mail: amadiuchennainno@gmail.com, abokoigboye@gmail.com

ABSTRACT

This research focused on Arima modeling technique to the forecasting of Nigerian Gross Domestic Product between the period of 1980 – 2011. For statistical analysis we have used graphical methods to display data distributions, Autocorrelation Function (ACF), Partial Autocorrelation Functions (PACF), Residuals and forecast, and differencing to check for stationarity. The ARIMA (2,1,2) model was proposed for the data from the first differences which shows stability and invertibility. Forecasting were made for future observations up to fifteen (15) years which shows an increasing trend over time, and the Akaike Information Criteria (AIC) and the adjusted multiple correlation coefficient (adjusted R-square) provide a good summary of the total variability explained by the chosen fitted model.