Rice Production In Bangladesh Employing By Arima Model

Abstract

The present study was carried out to estimate growth pattern and also examine the best ARIMA model to efficiently forecasting Aus, Aman and Boro rice production in Bangladesh. It appeared that the time series data for Aus and Aman were 1st order homogenous stationary but Boro was 2nd order stationary. The study revealed that the best models were ARIMA (4,1,4), ARIMA (2,1,1), and ARIMA (2,2,3) for Aus, Aman, and Boro rice production, respectively. The analysis indicated that short-term forecasts were more efficient for ARIMA models compared to the deterministic models. The production uncertainty of rice could be minimized if production were forecasted well and necessary steps were taken against losses. The findings of this study would be more useful for policy makers, researchers as well as producers in order to forecast future national rice production more accurately in the short run.   Keywords: Production; ARIMA model; forecasting of rice. DOI: http://dx.doi.org/10.3329/bjar.v36i1.9229 BJAR 2011; 36(1): 51-62