R. Moghaddasi; M. Zhale Rajabi
Abstract
AbstractAutoregressive integrated moving average (ARIMA) has been one of the widely used linear models in time series forecasting during the past three decades. Recent studies revealed the superiority of Artificial Neural Network (ANN) over traditional linear models in forecasting. But neither ARIMA ...
Read More
AbstractAutoregressive integrated moving average (ARIMA) has been one of the widely used linear models in time series forecasting during the past three decades. Recent studies revealed the superiority of Artificial Neural Network (ANN) over traditional linear models in forecasting. But neither ARIMA nor ANNs can be adequate in modeling and forecasting time series since the first model cannot deal with nonlinear relationships and the latter one is not able to handle both linear and nonlinear patterns simultaneously. Hence by combining ARIMA with ANN and designing the hybrid model, data relationship can be modeled more accurately. In this research, a hybrid of ARIMA and ANN models is designed and its prediction performance is compared with those of competing models. Forecasting performance is examined using common criteria such as MSE, RMSE and MAD. Also the significance of any difference between these measures is tested through application of Granger and Newbold statistic. Forecasting results for world wheat price data indicates that combined model significantly improves accuracy achieved by separate models.
M. Rafati; Y. Azarinfar; R. Mohammadzadeh
Abstract
AbstractThe aim of this study was to selecting the suitable model for forecast land, production and Price of sugar beet in Iran. For this purpose, Models applied to forecast are ARIMA, Single and Double Exponential Smoothing, Harmonic, Artificial Neural Network and ARCH for period 1993-2008. Results ...
Read More
AbstractThe aim of this study was to selecting the suitable model for forecast land, production and Price of sugar beet in Iran. For this purpose, Models applied to forecast are ARIMA, Single and Double Exponential Smoothing, Harmonic, Artificial Neural Network and ARCH for period 1993-2008. Results of Durbin-Watson tests, land, production and price of sugar beet series were found non stochastic and predictable. Based on the lowest forecasting error criterion, ARIMA is the best model for forecast production and price of sugar beet series. But in orther to forecast land of sugar beet, Neural Network model is the best. Hence, using the forecast method can affect on different policy about production via forecasting the fluctuation variables.Jel Classification: Q11 – D12 – C32 – C22
M.R. Zare Mehrjerdi; S. Negarchi
Abstract
AbstractNowadays, due to the environmental uncertainty and rapid development of new technologies, economic variables are often predicted by using less data and short-term timeframes. Therefore, prediction methods which require fewer amounts of data are needed. Auto Regressive Integrated Moving Average ...
Read More
AbstractNowadays, due to the environmental uncertainty and rapid development of new technologies, economic variables are often predicted by using less data and short-term timeframes. Therefore, prediction methods which require fewer amounts of data are needed. Auto Regressive Integrated Moving Average (ARIMA) model and Artificial Neural Networks (ANNs) need large amounts of data to achieve accurate results, however Fuzzy Regression (FR) models, compared with other models, are more suitable for conditions with less attainable data. In order to solve the above mentioned problem and to achieve more accurate results, in the present paper three methods have been evaluated: Auto Regressive Integrated Moving Average (ARIMA), Fuzzy Regression (FR), and Fuzzy Auto Regressive Integrated Moving Average (FARIMA) which is resulted by combining ARIMA and Fuzzy methods. Comparing the accuracy of predictions, based on two criteria RMSE and R2, indicated that Fuzzy Auto Regressive Integrated Moving Average (FARIMA) had the best results in forecasting the price index.Keywords: Price prediction, ARIMA, Fuzzy regression, FARIMA
S.M. Fahimifard; A.A. Keikha; M. Salarpour
Abstract
AbstractThis study is conducted to examine the transaction costs of obtaining credit from Bank Keshavarzi (BK). High transaction costs are stated as an important factor that limits rural households to access credit in rural areas in developing countries. The data collected from the bank and also by a ...
Read More
AbstractThis study is conducted to examine the transaction costs of obtaining credit from Bank Keshavarzi (BK). High transaction costs are stated as an important factor that limits rural households to access credit in rural areas in developing countries. The data collected from the bank and also by a survey in a multi-stage sampling technique in 1383-1384. After estimating transaction costs of borrowing and lending, the econometric models used to determine the factors that affect the transaction costs of access to credits. The results highlight the importance of transaction cost in the borrowing and lending process. The results reveal that the transaction costs of gaining credit are equivalent to 915510 Rials, that is, an additional 2.68 percent annual interest cost. The average transaction costs of credit supply by BK is 3.4 percent of total costs. The econometric results showed that the size of loan and the experience, education level and information of the borrower are important determinants of the transaction costs.JEI Classification: G21, G28
H. Mehrabi Boshrabadi; S. Koochakzadeh
Abstract
AbstractTo get ride of fragile and unsustainable single product export, a comprehensive knowledge of export potential and comparative advantage is required. Agricultural products can be considered as a suitable target for this purpose. For more efficient planning for agricultural products export, proper ...
Read More
AbstractTo get ride of fragile and unsustainable single product export, a comprehensive knowledge of export potential and comparative advantage is required. Agricultural products can be considered as a suitable target for this purpose. For more efficient planning for agricultural products export, proper forecasting is necessary. To achieve this goal, two methods were used and compared. First, an autoregressive integrated moving average (ARIMA) and second, artificial neural networks. For this purpose, the data were received from customhouse from 1961-2006. The data from 1961- 2002 were used for modeling and the last 4 years, were used for examination of forecasting power. Results indicated that artificial neural networks radial basis was more efficient in comparison with other neural networks methods and ARIMA for forecasting the quantity of agricultural products export. Finally, the quantities of agricultural products export forecasted for 2007-2011 by artificial neural networks radial basis.