Forecasting of Rabi Pulse Production in Odisha (India) by Using Autoregressive Integrated Moving Average (ARIMA) Technique
Current Journal of Applied Science and Technology,
The present study was carried out to forecast the production of rabi pulse in Odisha by using the forecast values of area and yield of rabi pulses obtained from the selected best fit Autoregressive Integrated Moving Average (ARIMA) model. The data from 1971-72 to 2010-11 are considered as training set data and used for model building and from 2011-12 to 2015-16 are considered as testing set data and used for cross-validation of the selected model on the basis of the absolute percentage error. The ARIMA models are fitted to the stationary data which may be the original data and/or the differenced data. The different ARIMA models are judged on the basis of Autocorrelation Function (ACF) and Partial autocorrelation Function (PACF) at various lags. The possible ARIMA models are selected on the basis of significant coefficient of autoregressive and moving average components. The best fitted models are selected on the basis of residual diagnostics test and model fit statistics. The ARIMA model found to be best fitted for area under rabi pulse and yield of rabi pulse are ARIMA (2,0,0) with constant and ARIMA (0,1,1) without constant respectively which are successfully cross-validated with the testing set data. The excellent fit ARIMA model has been used to forecast the area and yield of rabi pulse for the years 2016-17, 2017-18 and 2018-19. The forecast value of area shows an increase, where as, the forecast values of yield shows a decrease. The forecast values of production of rabi pulse obtained from the forecast values of area and yield of rabi pulse shows an increase which is due to the increase in forecast value of area. Thus emphasis must be laid on increasing the future yield of rabi pulse so as to achieve sufficient increase in production of rabi pulses which could ensure nutritional security to more extent.
How to Cite
Nelson C. The prediction performance of the FRB-MIT_PENN model of the US economy. The American Economic Review. 1972;62(5):902-917.
Newbold P, Granger CWJ. Experience with forecasting univariate time series and the combination of forecasts. Journal of the Royal Statistical Society. Series A. 1974; 137(2):131-165.
Vishwajith KP, Sahu PK, Dhekale BS, Mishra P. Modelling and Forecasting Sugarcane and Sugar Production in India. Indian Journal of Economics and Development. 2016;12(1):71-79.
Sahu PK, Vishwajith KP, Dhekale BS, Mishra P. Modelling and Forecasting of Area, Production, Yield and Total seeds of Rice and Wheat in SAARC countries and the world towards food security. American Journal of Applied Mathematics and Statistics. Science and Education Publishing, USA. 2015;3(1):34-48.
Mishra P, Sahu PK, Uday JPS. ARIMA modeling technique in analyzing and forecasting fertilizer Statistics in India. Trends in Biosciences Journal. 2014; 7(2):170-176.
Dhekale BS, Vishwajith KP, Sahu PK, Mishra P, Noman MD. Modeling and forecasting of tea production in West Bengal. Journal of Crop and Weed. 2014;10(2):94-103.
Mishra P, Fatih C, Niranjan HK, Tiwari S, Devi M, Dubey A. Modelling and forecasting of milk production in Chhattisgarh and India. Indian Journal of Animal Research; 2020.
Box GEP, Jenkins GM, Reinsel GC. Time series Analysis: Forecasting and Control. 4th Edition, John Wiley & Sons, Hoboken, New Jersey; 2007.
Ljung GM, Box GEP. On a measure of a lack of fit in time series models. Biometrika. 1978;65(2):297–303.
Lee R, Qian M, Shao Y. On rotational robustness of shapiro-wilk type tests for multivariate normality. Open Journal of Statistics. 2014;4(11):964-969.
Dash A, Dhakre DS, Bhattacharjee D. Forecasting of food grain production in Odisha by fitting ARIMA model. Journal of Pharmacognosy and Phytochemistry. 2017;6(6):1126-1132.
Abstract View: 816 times
PDF Download: 309 times