ARCH-GARCH Models Research Articles

Navigating the Future of Nifty ESG 100: Forecasting Price and Volatility with ARCH-GARCH Models & AR

Navigating the Future of Nifty ESG 100: Forecasting Price and Volatility with ARCH-GARCH Models & AR

Can technical indicators based on underlying assets help to predict implied volatility index

AbstractGiven the widespread use of technical analysis and the tight relationship between derivatives and the underlying assets, we employ the copula approach to investigate whether the technical indicators based on underlying assets convey extra information about the future movements of implied volatility (IV) indexes. The empirical results, based on long samples of five well‐known IV indexes, suggest that although the technical indicators are not informative for forecasting the future prices of IV indexes, they can provide extra information about the size of forecasting errors of the IV indexes. The findings are also robust to the impact of COVID‐19. The technical indicators are then used to extend Threshold ARCH and Exponencial GARCH models for improving the estimation of Value at Risks (VaRs). The out‐of‐sample forecast results show that the proposed model outperforms the benchmark in estimating the VaRs. These findings have implications for pricing options of IV indexes and managing the risks of IV‐related portfolios.

Time Series Analysis of Crime Rate in Osun State Nigeria Using Skellam Garch(1,1) Models

The manifestation of urban crime and other social vices causing anti-moral, anti-social behaviours as well as criminal damage to both public and private properties in Nigeria with the consequential effect of spontaneous and uncontrollable urban growth, high-level poverty rate, distortion of city peace and tranquillity has become an issue of national discourse. The paper employed ARCH and Skellam GARCH models to forecast the likely crime rate trend within the next five years. The Skellam-GARCH model performs better as a crime forecasting model than the ARCH model.

Volatility GARCH models with the ordered weighted average (OWA) operators

Volatility is an important issue for companies, policy-makers, and researches. Autoregressive conditional heteroscedasticity (ARCH) and generalized ARCH (GARCH) models are frequently used to study volatility. However, forecasting efficiency tends to fail when complex data is used. This paper proposes the use of ordered weighted average (OWA) operators in combination with ordinary least squares (OLS) to create an estimator that can treat high degrees of uncertainty. In the application of the ARCH-GARCH models, we develop approaches with the OWA and the induced OWA operator. Some further generalizations are also developed by using generalized means. The main advantage of this new methodology is to add additional information to the process of estimating the models according to the attitudinal character of the decision-maker. Finally, the work presents an application in the volatility of the MX/US exchange rate, where the efficiency of the OWA operators in forecasting is proved.

APPLICATION OF SKEWNESS IN PASSING OF ARCH-GARCH MODEL COMMENCE FOR CURRENCY PORTFOLIOS

The paper uses Coskewness as risk measure, average return and gives detail of efficient skewness (gamma) of a diversity of currency portfolios. This paper also applies ARCH-GARCH model, significant properties of GARCH allow to efficient modeling financial time series having obese conclusions. Then, we connect Coskewness with ARCH-GARCH models to optimize currency portfolio. To conclude, an empirical study of ten currency portfolios from Pakistan currency exchange market is performed and all the results suggest that Coskewness can better characterized the risk-adjustment and average variance and the performance of ARCH-GARCH model is better than that of ARIMA model in portfolio optimization.

The Modelling of Exchange Rate Volatility Using Arch-Garch Models: The Case of Turkey

This study investigates the most appropriate method for modelling the volatility for nominal exchange rate by using the ARCH type models. The research covers the period of 2002-2017 of nominal exchange rate using daily data. It is observed that the volatility of nominal exchange rate has the ARCH effect and the most appropriate model for forecasting the volatility of nominal exchange rate is GARCH(1,2) because it has the lowest Akaike Information Criterion. Furthermore, during the crises and uncertain periods, the volatility of nominal exchange rate series increases and volatility clustering is observed, meaning high volatility tends to follow high volatility and it is true for vice versa.

AR–ARCH Type Artificial Neural Network for Forecasting

Real-world time series such as econometric time series are rarely linear and they have characteristics of volatility. Although autoregressive conditional heteroscedasticity models have used for forecasting financial time series, these models are specific models for time series, so they are not generally applied for all-time series. ARCH–GARCH models usually applied on financial time series. Because, since these time series include features like volatility clustering and leptokurtic and therefore cause problem of heteroscedastic. These problems can be handled thanks to these models. However, These model can be modelled by ARCH–GARCH models only if they include arch effect after being checked that whether ARCH effect exists or not. Therefore, in recent years artificial neural networks have been commonly used various fields by many researchers for any nonlinear-or linear time series, especially multiplicative neuron model-based artificial neural networks are commonly used that have successful forecasting results. It is known that hybrid methods in artificial neural networks are useful techniques for forecasting time series. In this study, a new hybrid forecasting method has a multiplicative neural network structure AR–ARCH–ANN model has been proposed. The proposed method is a recurrent model and also it can model volatility with having autoregressive conditional heteroscedasticity structure. In the proposed approach, particle swarm optimization is used for training neural network. Possibilities of avoiding local minimum traps are increased by this algorithm in using trained process. Istanbul Stock Exchange daily data sets from 2011 to 2013 and some time series in using for 2016 International Time Series Forecasting Competition are obtained to evaluate the forecasting performance of AR–ARCH–ANN. Then, results produced by the proposed method were compared with other methods and it has better performance from other methods.

Volatility Analysis of the Romanian Exchange Rate

Volatility has been traditionally analysed from the perspective of economic cycles and only recently as an autonomous process with a major influence on different macroeconomic approaches. Volatility is associated with risk in the sense that it offers a measure of possible variations of economic variables and the increased volatility of the markets can trigger economic crises as it can be seen in economic history. The paper intends to analyse the volatility of the leu/euro exchange rate taken into account the influence of the volatility of other currencies and other fundamental macroeconomic variables. The analysis is based on specific methods for high frequency time series. The database is comprised of daily time series for the period 05.01.2000-31.08.2013. The application of different ARCH-GARCH models indicate that the volatility of the leu/euro exchange rate follows an ARCH process, that there is a high asymmetry in the evaluation of information regarding the evolution of the exchange rate and that the exchange rate returns are correlated with volatility.

A Comparison of Linear and Nonlinear Models in Forecasting Market Risk: The Evidence from Turkish Derivative Exchange

This paper aims to compare the volatility forecasting performance of linear and nonlinear models for ISE-30 future index which is traded in Turkish Derivatives Exchangefor the period between 04.02.2005-17.06.2011. As a result of analyses, we conclude that ANN model has better forecasting performance than traditional ARCH-GARCH models. This result is important in many fields of finance such as investment decisions, asset pricing, portfolio allocation and risk management

Forecasting Volatility of Dhaka Stock Exchange: Linear Vs Non-linear models

Prior information about a financial market is very essential for investor to invest money on parches share from the stock market which can strengthen the economy. The study examines the relative ability of various models to forecast daily stock indexes future volatility. The forecasting models that employed from simple to relatively complex ARCH-class models. It is found that among linear models of stock indexes volatility, the moving average model ranks first using root mean square error, mean absolute percent error, Theil-U and Linex loss function criteria. We also examine five nonlinear models. These models are ARCH, GARCH, EGARCH, TGARCH and restricted GARCH models. We find that nonlinear models failed to dominate linear models utilizing different error measurement criteria and moving average model appears to be the best. Then we forecast the next two months future stock index price volatility by the best (moving average) model.

An Assessment of Renewable Energy in Bangladesh through ARIMA, Holt’s, ARCH-GARCH Models

Forecasting of the Renewable Energy plays a major role in optimal decision formula for government and industrial sector in Bangladesh. This research is based on time series modeling with special application to solar energy data for Dhaka city. Three families of time series models namely, the autoregressive integrated moving average models, Holt’s linear exponential smoothing, and the autoregressive conditional heteroscedastic (with their extensions to generalized autoregressive conditional heteroscedastic) models were fitted to the data. The goodness of fit is performed via the Akaike information criteria, Schwartz Bayesian criteria. It was established that the generalized autoregressive conditional heteroscedastic model was superior to the autoregressive integrated moving average model and Holt’s linear exponential smoothing because the data was characterized by changing mean and variance.DOI: http://dx.doi.org/10.3329/dujs.v60i2.11486 Dhaka Univ. J. Sci. 60(2): 159-162, 2012 (July)

International propagation of shocks: an evaluation of contagion effects for some Latin American countries

In this paper we analyse the spread of shocks across asset markets in eight Latin American countries. First, we measure the extent of market reactions with the principal components analysis, and second, we investiga'te the volatility of asset markets based on ARCH-GARCH models as a function of the principal components retained in the first stage. Our results do not support the existence of financial contagion, but they do support interdependence in most cases along with a slight increase in the sensitivity of markets to recent shocks.

Long Memory in Stock Market Volatility: Indian Evidences

Long memory in variance or volatility refers to a slow hyperbolic decay in auto-correlation functions of the squared or log-squared returns. GARCH models extensively used in empirical analysis do not account for long memory in volatility. The present paper examines the issue of long memory in volatility in the context of Indian stock market using the fractionally integrated generalized autoregressive conditional heteroscedasticity (FIGARCH) model. For the purpose, daily values of 38 indices from both National Stock Exchange (NSE) and Bombay Stock Exchange (BSE) are used. The results of the study confirm presence of long memory in volatility of all the index returns. This shows that FIGARCH model better describes the persistence in volatility than the conventional ARCH-GARCH models.

Granular RBF NN Approach and Statistical Methods Applied to Modelling and Forecasting High Frequency Data

We examine the ARCH-GARCH models for the forecasting of the bond price time series provided by VUB bank and make comparisons the forecast accuracy with the class of RBF neural network models. A limited statistical or computer science theory exists on how to design the architecture of RBF networks for some specific nonlinear time series, which allows for exhaustive study of the underlying dynamics, and determination of their parameters. To illustrate the forecasting performance of these approaches the learning aspects of RBF networks are presented and an application is included. We show a new approach of function estimation for nonlinear time series model by means of a granular neural network based on Gaussian activation function modelled by cloud concept. In a comparative study is shown, that the presented approach is able to model and predict high frequency data with reasonable accuracy and more efficient than statistical methods.

Application of ARCH-GARCH Models and Feed-Forward Neural Networks with Bayesian Regularization in Capital Asset Pricing Model: The Case of Two Stocks in Athens Exchange Stock Market

In this paper we apply CAPM model in the financial time series of the share prices of Technology-Software Sector in Athens Exchange stock market for the period January 1st of 2002 to June 30th of 2008 for the enterprises Dionic and Coca-Cola. In one stock we apply the OLS method and in the other we apply the a GARCH model because of heteroscedasticity presence. In the following phase we simulate the forecasting results with feed-forward neural networks and we compare the new forecasts with that we obtain by OLS and GARCH estimation. The forecasting period is July 1st to July 24th of 2008.

International Propagation of Shocks: An Evaluation of Contagion Effects for Some Latin American Countries

In this paper we analyze the spread of shocks across assets markets in eight Latin-American countries. First, we measure the extent of markets reactions with the Principal Components Analysis. And second, we investigate the volatility of assets markets based in ARCH-GARCH models in function of the principal components retained in the first stage. Our results do not support the existence of financial contagion, but of interdependence in most of the cases and a slight increase in the sensibility of markets to recent shocks.

Granular RBF NN Approach and Statistical Methods Applied to Modelling and Forecasting High Frequency Data

We examine the ARCH-GARCH models for the forecasting of the bond price time series provided by VUB bank and make comparisons the forecast accuracy with the class of RBF neural network models. A limited statistical or computer science theory exists on how to design the architecture of RBF networks for some specific nonlinear time series, which allows for exhaustive study of the underlying dynamics, and determination of their parameters. To illustrate the forecasting performance of these approaches the learning aspects of RBF networks are presented and an application is included. We show a new approach of function estimation for nonlinear time series model by means of a granular neural network based on Gaussian activation function modelled by cloud concept. In a comparative study is shown, that the presented approach is able to model and predict high frequency data with reasonable accuracy and more efficient than statistical methods.

An application of three bivariate time‐varying volatility models

AbstractThe multivariate time‐varying volatility models have recently attracted a lot of attention in the statistics/econometrics community. We apply two bivariate ARCH–GARCH models and a bivariate unobserved ARCH model to a series of exchange rates, and we estimate the parameters using Bayesian inference. We compare these models using a posterior predictive model diagnostic. Copyright © 2001 John Wiley & Sons, Ltd.

Volatility Persistence and Switching ARCH in Japanese Stock Returns

Standard ARCH-GARCH models usually impute a high degree of persistence toconditional volatility. This persistence may be spurious if theconditional volatility is subject to structural change. This paper appliesthe Switching ARCH(SWARCH) model of Hamilton and Susmel (1994) toinvestigate regime shifts and volatility persistence in the Japanese stockmarket. We find that the SWARCH model provides a better description of thedata and implies a much lower degree of volatility persistence thanconventional ARCH models.

Volatility Clustering, Asymmetry and Hysteresis in Stock Returns: International Evidence

Encompassing a very broad family of ARCH-GARCH models we show that heteroskedasticity, already well documented for the US market, is a worldwide phenomenon. The AT-GARCH (1,1) model, where volatility rises more in response to bad news than to good news, and where news is considered bad only below a certain level, is found to be a remarkably robust representation of worldwide stock market returns. The residual structure is then captured by extending ATGARCH (1,1) to an hysteresis model, HGARCH, where we model structured memory effects from past innovations. Obviously, this feature relates to the psychology of the markets and the way traders process information. For the French stock market we show that a shock of either sign may affect volatility differently, depending on the recent past being characterized by either all positive or all negative returns. In the same way a longer term trend of either sign may also influence the impact on volatility of current innovations. It is found that bad news is discounted very quickly in volatility, this effect is reinforced when it comes after a negative trend in the stock index. On the opposite, good news has a very small impact on volatility except when it is clustered over a few days, which in this case reduces volatility substantially.