ARIMA Modelling for Forecasting of Rice Production: A Case Study of India

DOI: 10.18805/ag.D-5029    | Article Id: D-5029 | Page : 404-407
Citation :- ARIMA Modelling for Forecasting of Rice Production: A Case Study of India.Agricultural Science Digest.2020.(40):404-407
Sunali Mahajan, Manish Sharma, Amit Gupta sunali12mahajan@gmail.com
Address : Division of Statistics and Computer Science, Sher-e-Kashmir University of Agricultural Sciences and Technology, Jammu-180 009, Jammu and Kashmir, India.
 
Submitted Date : 29-08-2019
Accepted Date : 23-05-2020

Abstract

Background: India has been the top exporter in global rice trade, accounting for more than 20% of the export in the last four years. With the increasing demand for rice globally, exports are increasing from India. This factor is helping to enhance the production capacities of rice in India. The rice production has increased by 3.5 times in the last 60 years. So, forecasting of any agricultural produce play a major role in optimal decision formulae for government and agricultural sector in India. This study aimed to increase the production of rice for next four years, by using an appropriate model.
Methods: To develop an appropriate model for rice production, time series data from 1950-51 to 2016-17 have been used, through the Box Jenkins auto regressive integrated moving average (ARIMA) methodology. 
Result: The diagnostic tests showed that ARIMA (0 2 2) model is appropriate for forecasting on the basis of the significance of the model, parameters, Akaike Information Criteria (AIC), Schwartz Bayesian Information Criterion (SBIC) and R2. The forecasted results suggested that there are expectations of increasing the rice production in India. The proposed forecasting model will help us to estimate the rice production for future and found that rice production of India would become 110.64 MT in 2020-21. This study clearly indicates that forecasting is very useful for policy makers to anticipate future needs of rice and its export. Moreover, this would also prove helpful in shaping the national policy of economic growth and self-sufficiency in food grain.

Keywords

Akaike Information Criteria ARIMA Forecast Rice production Schwartz Bayesian Information Criterion

References

  1. Akaike, H. (1979). A bayesian extension of the minimum AIC procedure of autoregressive model fitting. Biometrica. 66: 237-242.
  2. Box, G.E.P., Jenkin, G.M. (1968). Discrete models for forecasting and control. In: Encyclopedia of Linguistics, Information and Control, 1-6, Oxford, Pergamon Press.
  3. Box, G.E.P., Jenkin, G.M. (1976). Time Series of Analysis, Forecasting and Control, San Franscico, Holden-Day, California, USA.
  4. Dickey, D., Fuller, W. (1981). Likelihood Ratio Statistics for Autoregressive Time Series with a Unit Root. Econometrica. 49: 1057-1072.
  5. Fuller, W. (1996). Introduction to Statistical Time Series, Second Edition. John Wiley, New York. 
  6. Granger, C. W. J., Newbold, P. (1973). Some comments on the evaluation of forecasts. Applied Economics. 5: 35-47.
  7. http://eands.dacnet.nic.in
  8. https://www.jmp.com 
  9. https://www.thehindu.com 
  10. Schwarz, G. (1978). Estimating the dimension of a model. Annals of Statistics. 6: 461-464.

Global Footprints