Research Articles
Forecasting of Paddy Production in Sri Lanka: A Time Series Analysis using ARIMA Model
Authors:
V Sivapathasundaram ,
University of Peradeniya, LK
About V
Postgraduate Institute of Agriculture
C Bogahawatte
University of Peradeniya, LK
About C
Postgraduate Institute of Agriculture
Abstract
Forecasting of paddy production is a need for planning purposes and import policy of rice should be based on such forecasts. Even though Sri Lanka has achieved self sufficiency in rice the expenditure on rice sector has increased continuously. The objectives of this study are to investigate the past, present and future trends of paddy production in Sri Lanka and to develop a time series model to detect the long term trend and prediction for future changes of paddy production for the three leading years. Autoregressive Integrated Moving Average (ARIMA) was used to fit the data set which is complementary to the trend regression approach and forecasting of the concerned variable to the near future. Time series forecasting analysis utilized the secondary data of the Department of Census and Statistics of Sri Lanka for the period of 1952 to 2010. Non-stationarity in mean was corrected through differencing of the data of order 1. ARIMA (2, 1, 0) was the most suitable model used as this model has the lowest AIC and BIC values. The Mean Absolute Percentage Error (MAPE) for paddy production was 10.5. The forecasts for paddy production during 2011 to 2013 were 4.07, 4.12 and 4.22 million Mt respectively, and the production for the year 2011 and 2012 was lower than in 2010. However in later year 2013 the production was higher. This model can be used by researchers for forecasting of paddy production in Sri Lanka. But, it should be updated continuously with incorporation of recent data.
Tropical Agricultural Research Vol. 24(1): 21-30(2012)
DOI: http://dx.doi.org/10.4038/tar.v24i1.7986
How to Cite:
Sivapathasundaram, V. and Bogahawatte, C., 2015. Forecasting of Paddy Production in Sri Lanka: A Time Series Analysis using ARIMA Model. Tropical Agricultural Research, 24(1), pp.21–30. DOI: http://doi.org/10.4038/tar.v24i1.7986
Published on
23 Jan 2015.
Peer Reviewed
Downloads