استخدام نماذج ARFIMA في التنبؤ بمؤشر منظمة الأغذية و الزراعة

الملخص EN

In this study, we investigated the use of ARFIMA models in predicting indicator of Food and Agriculture Organization, and determine the value of the fractional difference parameter (d) for ARFIMA model, using three estimating methods, where Reisen (1994) or dSperio outperformed on the other two methods, R / S analysis and GPH, to obtain the ARFIMA model required for predicting the (FPI).

Statistical results also indicated that the most appropriate model to represent the data series of (FPI) is ARFIMA(2,0.418,2), with a value of fractional difference (d = 0.418), which has succeeded in all necessary statistical tests.

Using the ARFIMA(2,0.418,2) model to predict future values for (FPI) series; the results indicated to a rise in the prices during the period June/2014 to December/2014.