A Comparison of Error Correction Model with Fuzzy Regression in Forecasting Gross Domestic Product (GDP) in Iran

National accounts data are of the most important statistical tools in planning and making economic policy. Therefore, forecasting the main economic variables in the economy is of great importance. Economic growth is one of the key macroeconomic variables, which gets top priority in forecasting. The purpose of this study is to identify the appropriate methodology for forecasting economic growth in Iran. This study introduces fuzzy regression model and its’ ability to forecast economic growth of Iran in comparison with Error Correction Model (ECM). To do this, the Iran’s GDP is modeled through ECM and Fuzzy regression models using annual data form 1959 to 2001. Then, Iran’s GDP growth is predicted for 2002-2012. Finally, the performances of these models are compared using common criteria for evaluating forecast accuracy including mean absolute error (MAE), root mean square Error (RMSE), mean absolute percentage error (MAPE) and Theil’s inequality coefficient (TIC). The results indicate that the performance of fuzzy regression is far better than that of ECM in predicting GDP growth in Iran. Moreover, forecast accuracy of fuzzy regression model is of statistically significant difference in comparison with ECM model.