Yazar "Bildirici M." seçeneğine göre listele
Listeleniyor 1 - 4 / 4
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Asymmetric power and fractionally integrated support vector and neural network GARCH models with an application to forecasting financial returns in ise100 stock index(Academy of Economic Studies, 2014) Bildirici M.; Ersin Ö.Ö.The study aims to augment commonly applied volatility models with support vector machines and neural networks. Further, fractional integration and asymmetric powers will be introduced. The proposed modeling strategy benefits from neural network based GARCH models and SVR-GARCH models. Following these approaches, the study proposed fractional integration and asymmetric power GARCH structures to obtain SVR-FIAPGARCH and NN-FIAPGARCH models to be evaluated in terms of learning algorithms. Models are evaluated for in-sample and out-of-sample forecasting of daily returns in Istanbul ISE100 stock index. Results suggest several findings: i. fractional integration and asymmetric power structures could be modeled with learning algorithms. ii. volatility clustering, asymmetry and nonlinearity characteristics are modeled more effectively with SVR-GARCH and MLP-GARCH models compared to the GARCH models. iii. SVR-GARCH models provided the lowest error criteria levels in out-of-sample and are closely followed by the MLP-GARCH models. © 2015, Academy of Economic Studies, All right reserved.Öğe Asymmetry in the environmental pollution, economic development and petrol price relationship: Mrs-var and nonlinear causality analyses(Institute for Economic Forecasting, 2019) Ersin Ö.; Bildirici M.The paper aims at assessing the nonlinear relations among the carbon dioxide (CO2) emissions, petrol prices and the level of economic prosperity in USA and UK for the 1861-2012 and 1871-2012 periods. By covering one of the largest samples, the paper achieves its novelty through the utilization of the Markov-switching based VAR and Granger causality methodologies to provide important insights regarding the shape of the Environmental Kuznets Curve. The selection of UK and USA is not only based on the availability of the largest data, but also on selecting countries that have gone through the stages of economic development in the sense of Rostow. In addition, the impact of the petrol prices is introduced to the environment-income relation. With this respect, the paper achieves a link between the literature of the regime-switching based business cycles and the environmental economics. The empirical findings of the paper show that: (i) the asymmetric impacts of the economic growth rates on emissions cannot be rejected both for the expansionary and for the recessionary periods in both countries in addition to the nonlinear effects of petrol prices, (ii) the nonlinear Granger causality results reveal bidirectional effects in both regimes which hold especially for the USA compared to the UK, (iii) the efficiency of the MRS-VAR models in capturing historical recession dates is confirmed since they coincide with major success to those reported by NBER and ECRI, (iv) the difference in persistence and durations of regimes should be taken into consideration. Within a policy perspective, the practical implications of the paper suggest further improvement in policies directed towards the environmental impact of economic growth in addition to petrol prices in different phases of the business cycles. The MRS-VAR findings also reveal practical implications regarding the shape of EKC: considering the size and the significance of the parameters in different regimes, the inverted U shape does not hold for the USA since the positive effects on emissions dominate in both regimes. In the UK, the negative effect is dominant only in regime 2. The paper also discusses the need of caution due to the shift of production from the developed to the far east-creating a derived demand of world’s environmental degradation. © 2019, Institute for Economic Forecasting. All rights reserved.Öğe A nonlinear analysis of monetary policy with dominance indices in turkey: MS-VAR approach(Institute for Economic Forecasting, 2017) Ersin Ö.; Bildirici M.The study focuses on analyzing the policies followed in Turkey based on inflation targeting with an application of interest rate corridor policy in which the spread between the two policy rates, namely, the borrowing and lending rates. To overcome the difficulty of two different policy rates, two indices, the PDI and the MDI are utilized to capture the response of the monetary authority within a nonlinear Taylor rule context. The empirical findings for the Turkish economy with MS-VAR and MS-Granger causality analyses suggest that while the policy interest rates are determined in the spirit of the Taylor rule, the monetary policy involuntarily affirms inflation after the application of the policy, a finding that is consistent with the FTPL theory. As a result, as the central bank tries to establish price stability and financial stability with two policy interest rates, accepting higher inflation rates could be unavoidable. The results also are in favor of bi-directional nonlinear causality which led to important policy implications. © 2017, Institute for Economic Forecasting. All rights reserved.Öğe Nonlinearity, volatility and fractional integration in daily oil prices: Smooth transition autoregressive ST-FI(AP)GARCH models(Institute foe Economic Forecasting, 2014) Bildirici M.; Ersin Ö.Ö.The study aims to extend the GARCH type volatility models to their nonlinear TAR (Tong, 1990) and STAR-based (Terasvirta, 1994) counter parts where both the conditional mean and the conditional variance processes follow TAR and STAR nonlinearity. The paper further investigates the models under their fractional integration and asymmetric power variants. The STAR-based models are LSTAR-LST-GARCH, LSTAR-LST-FIGARCH, LSTAR-LST-FIPGARCH and LSTAR-LST-FIAPGARCH models, which may be easily applied to model and forecast various financial time series. In the empirical section, an application is provided to model the daily returns in WTI crude oil prices considering the regime shifts the crude oil prices were subject to during history. Models are evaluated in terms of their out-of-sample forecasting capabilities with equal forecast accuracy tests and also in terms of various error criteria. The results suggest that volatility clustering, asymmetry and nonlinearity characteristics are modeled more efficiently as compared to their single regime variants, such as the GARCH, FIGARCH and FIAPGARCH models. Further, the out-of-sample results suggest that the LSTAR-LST-FIAPGARCH model provides the best forecasting accuracy in terms of RMSE and MSE error criteria. © 2014 Institute foe Economic Forecasting. All rights reserved.