Statistical Modeling and Forecasting of Gram Pulse Area and Production of Pakistan

The main aim of this study is to forecast the area and production of gram pulse in Pakistan using best selected time series model based on time series data i.e. 1947-1948 to 2016-2017. The area and production of gram were forecasted over 2017-2018 to 2029-2030. A variety of time series models were applied to forecasts the gram area and production of Pakistan. The Akaike Information Criteria (AIC) and some others showed that the ARIMA (1, 1, 1) and ARIMA (2, 1, 2) are the more adequate models for gram area and production, respectively. Some diagnostic tests of the selected time series model are also considered to evaluate the quality of the selected model. Moreover, the quality, of the selected models is measured based on the minimum value of the mean error, root mean square error, mean percentage error, and mean percentage absolute error. From ARIMA (1, 1, 1) and ARIMA (2, 1, 2) model, we noticed that gram area and production of Pakistan are forecasted to be 2515.08 thousand acers and 518.325 thousand tons in 2030 under the condition that there is no unusual event occurred.