Area, Production and Productivity of Wheat (Triticum aestivum) in Gujarat State: Forecasting by Using ARIMA Models

The present investigation was carried out to fit Autoregressive Moving Average (ARIMA) models to arrive at a methodology that can precisely explain the fluctuations of area, production and productivity for wheat crop data in Gujarat state after checking the stationary condition. The data from year 1960−61 to 2012−13 were used for model fitting and forecasting five years ahead from the year 2012−13. The ARIMA models with different p, d and q were judged on the basis of auto correlation function (ACF) and partial auto correlation function (PACF) at various lags. Among different fitted ARIMA models, the final models were selected on the basis of significant autoregressive and moving average term, Akaike's Information Criterion (AIC), Schwartz-Bayesian Criterion (SBC), test of normality (Shapiro-Wilk test) and randomness of residual's (Run test) distribution. Among the ARIMA models, ARIMA (0, 1, 1) family model was found suitable to forecast the pattern of wheat area and production and ARIMA (1, 1, 0) was found suitable for forecasting of wheat productivity trend of Gujarat State. Forecasted values showed an increasing pattern in area, production and productivity of wheat in Gujarat State and predicted values for area, production and productivity of wheat in the year 2017−18 are 12989.2 hundred ha, 40296.9 thousand t and 3148.42 kg ha⁻¹ respectively.