An application of ARIMA for forecasting rapeseed and mustard area in Gujarat

Abstract

Rapeseed and mustard are the second most important oilseed crops in India. Soybean, groundnut and rapeseed and mustard are the major oilseed crops in India contributing around 84% to its total acreage. Forecasting is used to support effective and efficient decision-making and long-term planning. The study was carried out to develop forecasting model of area of rapeseed and mustard crop in Gujarat by using the time series data of 1991-92 to 2019-20 years. The polynomial models were fitted to the original data as well as three-year, four year and five year moving average data while, Autoregressive Integrated Moving Average (ARIMA) models were fitted to the original data on area of rapeseed and mustard crop in Gujarat state. Criteria of evaluation of model was highest R2, lowest value of RMSE and MAE, significant coefficient of model, lower value of Akaike’s Information Criteria (AIC) and Schwartz-Bayesian Criteria (SBC) values, normality test and randomness test of residuals. Quadratic model on original data and ARIMA (0, 1, 3) model were found to be most suitable to explain the pattern of area of rapeseed and mustard crop in Gujarat.