فصلنامه نظریه های کاربردی اقتصاد
پیاپی 3 (زمستان 1393)

This article aims to study the predictability of daily return of global gold price، using data during the period 2011/07/25 to 2012/12/17. For this purpose، using Scheinnkman، Dechert & Brock Test (BDS)، we try to model the linearity، nonlinearity and chaos of the series under consideration. The results is indicative of the rejection of the hypothesis that the gold price daily return is stochastic، which in turn confirms the predictability of the series. The results of the linear model confirm the nonlinearity behavior of the series. Then، an ANFIS neuro-fuzzy model was designed to predict gold price daily return. To carry out this research، we use ARIMA and GARCH models to eliminate linear and nonlinear impacts of the gold price daily return، respectively. Next، using the several criterions، we compare the results of two models- ARIMA as linear model and GARCH as nonlinear model. As expected، ANFIS linear model presents a better prediction than ARIMA and GARCH models. Finally، using Morgan-Granger-Newbold statistics (MGN)، we investigate the statistical significance of the divergence between predictions of the models. The results indicates a significant difference between the predictions produced by nonlinear and linear ARMA models.

Exchange rate has key role in determining the degree of international competition and domestic economic situation، Therefore، investigating factors affecting the exchange rate will be helpful for trade policies. However، the effect of these factors on exchange rate often associated with ambiguity and uncertainty، so the use of fuzzy regression for estimating the effects of these variables on the exchange rate might be helpful. Because fuzzy regression estimates interval of possible values ​​for coefficient، whereas classical regression estimates only a certain amount for coefficients. The purpose of this study was to determine the factors affecting the real effective exchange rate in Iran using fuzzy regression in the period 2002 to 2010. In this context، the variables productivity growth، government spending، trade policies، oil prices and the currency held by the public are being used as important factors affecting the real exchange rate. According to results productivity growth rates and government spending have positive impact and oil prices، currency held by the public and trade policies have a negative effect on real effective exchange rate. Also، the impact of currency held by the public and oil prices is ambiguous. Hence، the interval estimates of coefficients are used to express the extent of their influence.

According to the strong relationship between a country''s economic growth and energy consumption and also due to high flexibility of Electricity and the rising share of its in countrie’s total energy - particularly in the developing world، Predict of future trend of electricity consumption، plays an important role in formulation of energy policy. There have been a number of forecasting models based on various forms of the logistic growth curve. This paper investigates the effectiveness of two forms of Harvey models and a Logistic model for forecasting electricity consumption in Iran for the period 1391-1400. The three growth curve models are applied to the Domestic، Agriculture، Industry and service sectors and Total electricity consumption in Iran. Mean absolute percentage error (MAPE) and the Durbin Watson statistic (DW) are used in the comparison of the three models; In order to investigate goodness of fit to historical data and forecasting accuracy. The comparison revealed that the Harvey model is a very appropriate candidate for forecasting electricity consumption in Iran.

Regional trade، boosted by trade integration and regional cooperation، is an important factor for countries trade growth. Free trade zones often facilitate trade between countries and increases trade. Aras free zone could works as a connecting bridge between Asia and Europe and enhances trade and economic growth. This study attempts to investigate the role and status of Aras free trade-industrial zone in trade development though the estimation of trade potentials with CIS countries، China and Turkey as the main trade partners in the region. The estimates of export and import potentials revealed the existence of high trade potentials between Aras free trade zone and aforementioned countries. Also، the results of trade complementarity estimates using cosine index indicated that Georgia، Azerbaijan and Kazakhstan had the highest export complementarity while، China، Turkey and Belarus had the highest import complementarity in the region. The study shows that given the current trade between Aras free trade zone and the countries، it is possible to increase trade volume by about ten folds.

Failure to meet the demand for e-banking services with the necessary infrastructure can cause many problems for a society and the process of economic activity in a society. Therefore، for this type of service forecasting the changes in demand is important to provide the infrastructure to meet the demand. The main purpose of this paper is forecasting the demand for e-banking services using two methods، artificial neural networks and SARIMA models، comparing two methods and volume of demand with infrastructures in Iran. This research sample consists of 88 observed transactions through 6 current channels of the banking network since Tir 1385 to Mehr 1392. Also by using these models، the demand is forecasted to the end of Aban 1393. The results indicate a continuing increasing trend and also show advantage of artificial neural networks to SARIMA model. Therefore، serious attention to infrastructure of electronic banking services is essential.

Many studies in the economic literature have devoted to analysis the effect of economic freedom on the economic growth and income per capita، but less study have analyzed the effect of economic freedom on the economic fluctuations. This Study has analyzed the effect of economic freedom on the economic fluctuations for 48 developing countries over the time period 2000-2010. To measure economic fluctuations two indices، “standard deviation of GDP growth” and “GDP fluctuations”، and for economic freedom “Fraser Institute Index” have been used. Models estimation has done by using cross section and panel data and results show that an increase in the economic freedom index reduces economic fluctuations.