Forecasting Gross Domestic Product In Nigeria Using Box-Jenkins Methodology

Abstract

Gross domestic product(GDP) is an important tool for measuring the quality of the overall economic activity in a country within a specified period of time. This study aimed at providing a model that can be used to forecast gross domestic product in Nigeria using the Box-Jenkins approach. Quarterly data on Nigerian GDP from the first quarter of 1990 to the second quarter of 2013 were used for this purpose. The time plot and preliminary analyses of the data called for log transformation and first order differencing of the data to achieve stationarity. Plots of the autocorrelation function (ACF) and partial autocorrelation function (PACF) of the transformed and differenced series suggested that SARIMA (2, 1, 2)x(1, 0, 1)4 be fitted to the data. The ACF and PACF of the residuals from the fitted model behaved like those of a white noise process. These confirmed the adequacy of the fitted model. The model was then used to forecast GPD in Nigeria for a period of one year.