:: 2, Issue 3 (quarterly journal modern theories of economy,vol2,no.3,(ser4),dec,2014 2014) ::
TFI 2014, 2(3): 37-54 Back to browse issues page
Comparison of ARIMA, Fuzzy Regression and Exponential Smoothing methods in the value added of the industrial sector forecasting
Samaneh Negarchi * , Ebrahim Javdan , Abdolmajid Jalaee
Abstract:   (1204 Views)
Nowadays, forecast economic variables play an important role in economic planning and policy making and a variety of methods to forecasting economic variables are used. Although it may be accurate in some cases is not important in predicting, but obviously many variables to predict the short-term policy is important.Due to the importance of industry and its share in GDP, in order to predict the value  added of the industrial sector in Iran during the period 1340-1389, in this paper four methods have been evaluated: Auto Regressive Integrated Moving Average (ARIMA), Fuzzy Regression (FR),  Single Exponential Smoothing with Trend (SEST) and Double Exponential Smoothing with Trend (DEST). Comparing the accuracy of predictions, based on two criteria RMSE and R2 indicated that single exponential smoothing with trend (SEST) and fuzzy regression (FR) had the best results in forecasting the value added of the industrial sector in Iran.
 
Keywords: Industry, Value Added, Forecasting
Full-Text [PDF 587 kb]   (308 Downloads)    
notification: Research | Subject: Special
Received: 2014/08/4 | Accepted: 2014/09/21 | Published: 2014/09/23


XML   Persian Abstract   Print



Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
2, Issue 3 (quarterly journal modern theories of economy,vol2,no.3,(ser4),dec,2014 2014) Back to browse issues page