ARIMA model and forecasting with three types of pulse prices in Bangladesh: a case study

Purpose - The purpose of this paper is to generate three types of forecasts, namely, historical, ex‐post and ex‐ante, using the world famous Box‐Jenkins time series models for motor, mash and mung prices in Bangladesh. Design/methodology/approach - The models on the basis of which these forecasts have been computed were selected by six important information criteria such as Akaike's Information Criterion (AIC), Schwarz's Bayesian Information Criterion (BIC), Theil'sR2, Theil'sR2, SE(σ) and Mean Absolute Percent Errors (MAPEs). In order to examine the forecasting performance of the selected models, three types of forecast errors were estimated, i.e. root mean square percent errors (RMSPEs), mean percent forecast errors (MPFEs) and Theil's inequality coefficients (TICs). Findings - The estimates suggest that in most cases the forecasting performances of the models in question are quite satisfactory. Originality/value - The models developed in this paper can be used for policy purposes as far as price forecasts of the commodities are concerned.