Estimation of conditional variance has lots of application reflecting economic, especially financial economics, social economics and political economics’ risk and volatility research. Therefore, obtaining accurate estimation of the conditional variance is especially important. Recently Hansen has modeled the conditional variance and realized volatility simultaneously which is known as Realized GARCH model. In this paper, we introduce a fuzzy coefficient in the Realized GARCH, and then compare this model with GARCH, EGARCH and GJR-GARCH methods as well as the RGARCH model with 2 different criteria of the realized volatility concerning Tehran Stock Exchange Index. The log likelihood value used to evaluate in-sample fitting. According to this criterion, our proposed model has a better fit than the rest of the models. To evaluate the accuracy of prediction of conditional variance, the rolling window method used with two MSE and QLIKE loss functions. The results indicate that our model, the Realized GARCH with fuzzy coefficient has the best performance with both loss functions.

In recent years, investment in gold has been remarkable for investors because of a recession in stock exchange. This increase in demand of gold caused increase in gold price. Because of increase in gold price, dealing of gold expanded and so volatility of gold price return increased intensly. So we have to use a model to predict volatility beside return to make decision for investment.Find a model that it can do a better forecast of price return volatility is a debatable topic in the finance literature. Around this topic some models have been presented and these models have some advantages and disadvantages. These models have been applied for predict of volatility of crude oil and exchange rate more than other fields. Between all models, GARCH models have been more applicable than others. So we use this group of models too, but in a different way. This way is a nonparametric approach to GARCH model that presented by Buhlman and McNeil for first time in 2002. In this research we use this approach to forecast volatility of gold price return and compare it with other GARCH models by two loss function (QLIKE-MSE). The result of this research shows that nonparametric GARCH has a better performance than the other GARCH models based on QLIKE loss function with a statistical significance, but based on MSE loss function we can’t judge.

In this paper we compare a set of different standard GARCH models with a group of Markov Regime-Switching GARCH (MRS-GARCH) in terms of their ability to forecast the petroleum futures markets volatility at horizons that range from one day to one month. To take into account the excessive persistence usually found in GARCH models that implies too smooth and too high volatility forecasts, MRS-GARCH models, where the parameters are allowed to switch between a low and a high volatility regime, are analyzed. Both gaussian and fat-tailed conditional distributions for the residuals are assumed, and the degrees of freedom can also be state-dependent to capture possible time-varying kurtosis. The forecasting performances of the competing models are evaluated with statistical loss functions. Under statistical losses, we use both tests of equal predictive ability of the Diebold-Mariano-type and test of superior predictive ability, such as White’s Reality Check and Hansen’s SPA test. The empirical analysis demonstrates that MRS-GARCH models do really outperform all standard GARCH models in forecasting volatility at shorter horizons according to a broad set of statistical loss functions. At longer horizons standard asymmetric GARCH models fare the best. All this tests reject the presence of a better model than the MRS-GARCH-t in this research.

Given the importance of oil prices, proper prediction of the OPEC Reference Basket can have an essential role in the immunization of economies in these countries against the effects of these fluctuations. This research is an effort to introduce an optimal model for modeling and predicting the fluctuations in OPEC crude oil prices. In this regard, we used data of daily oil prices between 2/1/1986 and 13/2/2017. According to this, the existence of long-term memory in the average equations and variance of crude oil prices were assessed and modeled and the result of the ARFIMA, confirms the existence of long-term memory in both the average equation and series variance. However, tests confirm non-linear and exponential behavior in crude oil prices. For this reason, results are specifically based on the information criteria and also MAPE and indicate the selection of a mixed model of partial augmented average movement and the model of conditional exponential Heteroscedasticity EGARCH (1,1) AFIRMA (4,0.09,3) as the best model for modeling and predicting the OPEC crude oil fluctuations in prices and lack of attention to exponential non-linear variance in the long term memory of crude oil prices can cause an error in the calculation of analysts and especially economic decision maker and deviation optimal policies.

In previous studies, the normal mixture, as well as the Markov process, were used to model the financial return, separately. In this study, the normal mixture model is extended to the Markov mixture of normals. The mixture weights in every state are considered time-varying and as a function of past observations, so the limit of constant weight assumption is removed. The proposed model is estimated using Bayesian inference and a Gibbs sampling algorithm has been created to compute posterior density. The performance of algorithm is tested with simulation, then a two-state Markov time-varying Mixed Normal-GARCH model (MMN) with one and two components in every state, as well as limited cases (mean zero), were compared by comparison of their likelihood function. Finally, the model is applied to S& P500 and TEPIX daily return and results show that MMN models with two components provide better results than MMN model with one component which is so-called Markov switching GARCH model.

In this study we compare a set of Markov Regime-Switching GARCH models in terms of their ability to forecast the Tehran stock market volatility at different time intervals. SW-GARCH models have been used to avoid the excessive persistence that usually found in GARCH models. In SW-GARCH models all parameters are allowed to switch between a low or high volatility regimes. Both Gaussian and fat-tailed conditional distributions are assumed for the residuals, and the degrees of freedom can also be state-dependent to capture possible time-varying kurtosis. Using stationary bootstrap and re-sampling, the forecasting performances of the competing models are evaluated by statistical loss functions. The empirical analysis demonstrates that SW-GARCH models outperform all standard GARCH models in forecasting volatility. Also, the SW-GARCH model with the t distribution for errors has the best performance in fitting a model and estimation.

By using the time series models, we can analysis financial data (in last and future time). In financial discussions, because of heteroskedastic observations, we can not use the classical time series models.We focus on popular practical models for financial time series, GARCH- type models, that were introduced for the first time by Bollerslev (1986). These models represent a very wide class of heteroskedastic econometric models. Time series models (GARCH models too), like regression models, have random errors. These errors have specific distributions.Since that, the GARCH models variability is not clear, thus, we use the Bayesian model selection methods to estimate the parameters of the model. In this method, by using the prior distributions on the parameters, we find the posterior distribution which has integral. Then, we can inference about the parameters.To explore the role of the posterior distribution, the most powerful technique is to use Markov Chain Monte Carlo (MCMC) computing methods such as the Gibbs sampler and the Metropolis Hasting (MH) algorithm. These algorithms enable to estimate the posterior distribution, but, they don't readily lend themselves to estimate aspects of the model probabilities. The most widely used one is the group of direct methods, such as the harmonic mean estimator, importance sampling and bridge sampling. Chib (1995 and 2001) proposed an indirect method for estimating model likelihoods from Gibbs sampling output. This idea has recently been extended to the output of the MH algorithm.We use a reversible jump MCMC strategy for generating samples from the joint posterior distribution based on the standard MH approach.

The main objective of this paper is determination of the price transmission mechanism in shrimp market of Iran by using bivariate GARCH model. The monthly data during 1380: 1-1394: 4 was used. The results indicated that the rate of change in retail prices is partially causes changes in wholesale prices. So that one unit increase in the retail price index would increase less than one unit (0. 2 units) Wholesale Price Index. Therefore, the price transmission in shrimp market is imperfect. The result of Houck method indicated that price transmission in the shrimp market is asymmetric and, speed of transmission in increasing price is more than decreasing prices. Therefore, according to the policy of reforming Shrimp imperfect market, the government must attended to non-price supporting Policies.

Forecasting the volatility of a financial asset has wide implications in finance. Conditional variance extracted from GARCH framework could be a suitable proxy of financial asset volatility. Option pricing, portfolio optimization and risk management are examples for implications of conditional variance forecasting. One of the most recent methods of volatility forecasting is Realized GARCH (RGARCH) that considers simultaneous model for both realized volatility and conditional variance at the same time. In this article, we estimate conditional variance with GARCH, EGARCH, GIR-GARCH and RGARCH with two realized volatility estimators using Tehran Exchange Price Index (TEPIX). We compared models, for in sample fitting, by the log likelihood value and used MSE and QLIKE lose functions to evaluate predicting accuracy. The results show that the RGARCH method for TEPIX outperforms the other methods in both ways. So, using RGARCH model in practical situations like pricing and risk management would tend to better results.

AbstractThe current research has been designed to design the overflow model of probability of financial helplessness in Iran's banking system with the approach of multivariate GARCH models.The statistical population of the includes the banks admitted to the Tehran Stock Exchange, which have been analyzed in the period of 2015 to 2019. To calculate them, time series data of banks' stock returns, equity value, book value of liabilities and daily value of assets have been used. The current research has investigated the probability of financial helplessness spillover to other banks by applying the KMV method and the concept of distance to default and by using the VAR model and the multivariate GARCH method (DCC-GARCH).The results of the research have shown that there is a significant relationship between the financial helplessness risk of banks with each other; Mellat Bank is exposed to the highest risk of helplessness contagion and Parsian Bank shows the least effectiveness. Based on the results of the model, the increase in operational risks of banks, including credit risk and market risk, has a significant effect on increasing the risk of financial helplessness, and this risk can spread to other banks in the banks' communication network and then to the entire economy.