An Autoregressive Integrated Moving Average (ARIMA) Model For Ghana’s Inflation (1985 – 2011).

Abstract

Inflation analysis is indispensable in a developing country like Ghana, which is struggling to achieve the Millennium Development goals. A literature gap exists in appropriate statistical model on economic variables in Ghana, thus motivating the authors to come up with a model that could be used to forecast inflation in Ghana. This paper presents a model of Ghana’s monthly inflation from January 1985 to December 2011 and use the model to forecast twelve (12) months inflation for Ghana. Using the Box – Jenkins (1976) framework, the autoregressive integrated moving average (ARIMA) was employed to fit a best model of ARIMA. The seasonal ARIMA model, SARIMA (1, 1, 2) (1, 0, 1) was chosen as the best fitting from the ARIMA family of models with least Akaike Information Criteria (AIC) of 1156.08 and Bayesian Information Criteria (BIC) of 1178.52. The selected model was used to forecast monthly inflation for Ghana for twelve (12) months.