Advances and Applications in Statistics
Volume 63, Issue 2, Pages 191 - 205
(August 2020) http://dx.doi.org/10.17654/AS063020191 |
|
TIME SERIES ARIMA MODEL FOR PREDICTION OF THAILAND’S MONTHLY AVERAGE CASSAVA STARCH DOMESTIC PRICE
Saowapa Chaipitak
|
Abstract: This study aims to build a time series autoregressive integrated moving average (ARIMA) model to forecast monthly average cassava starch domestic price of Thailand. The secondary data collected from the Thai Tapioca Starch Association (TTSA) between January 2011 and April 2020 was used to create the forecasting models. The adequate model was selected according to the minimum Akaike information criterion (AIC). The results indicate that the ARIMA (2, 0, 2) model can be used to predict monthly average cassava starch price with the lowest AIC. In addition, forecasting for lead times of eight months using the best fitted ARIMA model was conducted. These results will provide to farmers of reliable guidelines in planning and making decisions concerning cassava’s cultivation amount. |
Keywords and phrases: autoregressive operator, Box-Jenkins method, stationary.
|
|
Number of Downloads: 287 | Number of Views: 678 |
|