Forecasting model for the export quantity of concentrated latex

Abstract

The objective of this research is to construct the appropriate forecasting model for the export quantity of concentrated latex by the three time series analysis methods, which are Box-Jenkins method, Winters’ multiplicative exponential smoothing method, and combined forecasting method. Time series data from the website of Office of Agricultural Economics during January, 1998 to February, 2014 (194 values) are used and divided into two series. The first 182 values from January, 1998 until February, 2013 for the models prediction and the last 12 values from March, 2013 until February, 2014 for comparison the performance of forecasting models via the criterion of the lowest root mean squared error and the criterion of the highest correlation coefficient between existing values and forecasted values. Research findings indicated that, for all forecasting methods that have been studied, the most powerful method is the combined forecasting and the forecasting model is where and represent the single forecasts at time t from Box-Jenkins method and Winters’ multiplicative exponential smoothing method, respectively.