Empirical Approach to Modelling and Forecasting Inflation in Ghana

Inflation measures the relative changes in the prices of commodities and services over a period of time. In other to devise better policies to control the inflation rates it is necessary to know the pattern of inflation in the country. In this study, we employed an empirical approach to modelling monthly data in Ghana using the Box-Jenkins approach. The result showed that ARIMA (3, 1, 3) (2, 1, 1)12 model was appropriate for modelling the inflation rates. This model has the maximum log-likelihood of 242.90 and the least AIC of -465.80, AICc of -464.89, BIC of -430.51, RMSE of 0.080, MAPE of 1.902 and MAE of 0.054. Diagnostic test of the model residuals with the ARCH LM-test and Durbin-Watson test indicates that there was no ARCH effect and autocorrelation in the residuals respectively. Finally, an 11 months forecast for the year 2012 with the model revealed that Ghana is likely to experience single digit inflation values. Hence, we recommend that government and other policy makers should adopt appropriate measures to ensure that the objective of achieving single digit inflation value is met.