ARMA-GARCH Model Research Articles

Neural networks and ARMA-GARCH models for foreign exchange risk measurement and assessment

Neural networks and ARMA-GARCH models for foreign exchange risk measurement and assessment

TAIL DEPENDENCE OF COMMODITY FUTURES RETURNS IN THE AGRICULTURAL AND ENERGY SECTORS

The goal of this research was to examine tail dependence structures between selected commodity futures returns. Tail dependence, called also extremal dependence, was evaluated for the pairs of commodities coming from the same sector (energy or agricultural). The study covers the years 2018-2023, embracing the COVID-19 pandemic and the outbreak of the Russia-Ukraine war. To achieve the goal, bivariate dynamic models were applied to percentage log returns of commodity futures. Marginal distributions were described using the ARMA-GARCH models. Joint distributions were constructed using the symmetrized Joe-Clayton copula, which allowed to model asymmetric dependence in the tails of a distribution. Time variation of the copula parameters, here equal to tail dependence coefficients, was described using the evolution equations [Patton 2006]. In the energy sector, the dependence in both tails of analyzed distributions was relatively strong, dynamic and higher in the lower tail than in the upper tail. On the contrary, the agricultural sector lacks common patterns of tail dependency. This feature of the agricultural sector creates an opportunity for investors or risk managers to build well-diversified portfolios.

Unveiling change-point detection with ARMA-GARCH models

This paper delves into the asymptotic theory of a Cumulative Sum (CUSUM)-type test designed for detecting change points in the variance of AutoRegressive Moving-Average models, incorporating Generalized Autoregressive Conditional Heteroscedasticity innovations. We demonstrate that, under the null hypothesis (no change), the CUSUM test statistic converges to the supremum of a standard Brownian bridge. Using a Monte Carlo simulation, we highlight the strong performance of our proposed test when compared to the methods by Song and Kang. Furthermore, we provide a real-world data analysis to showcase the practical application of our test.

The spillover and leverage effects and trading volume of FinTech Exchange-Traded Funds

ABSTRACT This paper explores the spillover and leverage effects, as well as trading volume dynamics, of Financial, Technology, and FinTech Exchange-Traded Funds (ETFs) using ARMA-GARCH and ARMA-EGARCH models. The study indicates that these ETF sectors and the stock market index have significant connections and interdependencies, which can transmit shocks and volatility. Market fluctuations significantly impact the ETF sectors, with negative shocks having a more significant impact on volatility. Furthermore, increased volatility is linked to increased trading activity, which indicates active investor adjustments in uncertain periods. The practical implications of these findings for investors, portfolio managers, and policymakers are aimed at supporting portfolio diversification, risk management, and asset allocation decisions. Understanding the effect of market volatility on trading volumes can help improve trading strategies and liquidity management. The paper increases comprehension of spillover and leverage effects and trading volume in ETFs, enabling stakeholders to make well-informed decisions in the financial markets.

ANALISIS HUBUNGAN HARGA EMAS DAN PASAR SAHAM MENGGUNAKAN MIXED-COPULAS

Gold is considered as a reliable investment tool for long-term savings and/or investment portfolios. Investors who do not like high risks trust gold to be a safe haven commodity that can mitigate the impact of any financial crisis. Gold and stocks are often used as substitutes for each other, where the two have an inverse relationship. Copula is used to capture the dependence relationship between world gold prices and the stock indexes. The data used are the stock index data for the JKSE Indonesia), PSE (Phillipines), Nikkei 225 (Japan), HSI (Hong Kong), and world gold prices (XAU) from January 1, 2014 to December 31, 2019. From the data, the ARMA-GARCH model is made to solve the problem of autocorrelation and heteroscedasticity. Then, the correlation between assets is calculated using the rank correlation. Furthermore, four pairs of data are made from each stock index with the price of gold. Next, the best copula and the estimated Value-at-Risk (VaR) are sought for each portfolio. From the results of the selecting of the best copula for each pair of data, it is found that gold can be a safe haven asset in the Hong Kong's stock market. The VaR results show that the biggest loss is in the Japanese market.

The Impact of U.S. Economic Policy Uncertainty on the RMB: U.S. Dollar Exchange Rate - Case of China-US Trade War

On 6 July 2018, the United States began to impose 25% tariffs on $34 billion of Chinese goods. The trade war between China and the United States was officially launched. It lasted for more than a year, during which the two sides experienced six mutual tariff increases, which significantly impacted a few fields in China and the United States. This paper selects the RMB exchange rate to the US dollar as the research object; and takes the return of the RMB exchange rate as the data basis for modelling and analysis, intercepts its return data in the five years before and after the US-China trade war, taking the time when the United States imposed six additional tariffs on China as a dummy variable, and analyses the data by using the ARMA-GARCH model to study the impact of the RMB exchange rate by this trade war and to make predictions development of the RMB exchange rate, which will then make suggestions for China's economic.

An Empirical Study on Stock Returns of Chemical Industry Based on ARMA-GARCH Model--The Case of NIKKE Chemicals

This paper uses the ARMA-GARCH model to make predictions on the volatility of stock returns in China, selects the time series of daily returns of the representative enterprise of the chemical industry, NIKKE CHEMICAL, as the object of study, analyzes the stock returns of the enterprise over the past 6 years, and uses the ARMA model to make predictions of stock returns, and at the same time, joins the effect of volatility, and models the risk rate by using the GARCH model, and empirical evidence The results show that the chosen ARMA-GARCH model has a good fit to the time series of daily returns. This paper examines stock prices and analyses them by constructing a theoretical model that can provide advice for investment decisions in the stock market.

Predicting influenza-like illness trends based on sentinel surveillance data in China from 2011 to 2019: A modelling and comparative study1

BackgroundInfluenza is an acute respiratory infectious disease with a significant global disease burden. Additionally, the coronavirus disease 2019 pandemic and its related non-pharmaceutical interventions (NPIs) have introduced uncertainty to the spread of influenza. However, comparative studies on the performance of innovative models and approaches used for influenza prediction are limited. Therefore, this study aimed to predict the trend of influenza-like illness (ILI) in settings with diverse climate characteristics in China based on sentinel surveillance data using three approaches and evaluate and compare their predictive performance. MethodsThe generalized additive model (GAM), deep learning hybrid model based on Gate Recurrent Unit (GRU), and autoregressive moving average-generalized autoregressive conditional heteroscedasticity (ARMA—GARCH) model were established to predict the trends of ILI 1-, 2-, 3-, and 4-week-ahead in Beijing, Tianjin, Shanxi, Hubei, Chongqing, Guangdong, Hainan, and the Hong Kong Special Administrative Region in China, based on sentinel surveillance data from 2011 to 2019. Three relevant metrics, namely, Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE), and R squared, were calculated to evaluate and compare the goodness of fit and robustness of the three models. ResultsConsidering the MAPE, RMSE, and R squared values, the ARMA—GARCH model performed best, while the GRU-based deep learning hybrid model exhibited moderate performance and GAM made predictions with the least accuracy in the eight settings in China. Additionally, the models’ predictive performance declined as the weeks ahead increased. Furthermore, blocked cross-validation indicated that all models were robust to changes in data and had low risks of overfitting. ConclusionsOur study suggested that the ARMA—GARCH model exhibited the best accuracy in predicting ILI trends in China compared to the GAM and GRU-based deep learning hybrid model. Therefore, in the future, the ARMA—GARCH model may be used to predict ILI trends in public health practice across diverse climatic zones, thereby contributing to influenza control and prevention efforts.

Modelling The Volatility of Frankfurt Stock Exchange (DAX) Returns Using hybrid Models

Recently, the interest of researchers in the use of hybrid models in the process of analyzing model time series with fluctuations and forecasting fluctuations in financial time series has increased significantly. Hybrid ARMA-GARCH models were created for medium- and long-term forecasts of time series of financial market index prices: ARMA models are used to analyze their linear component, which is a combination of autoregressive models and moving average models, and GARCH models are used to analyze the nonlinear component. which are generalized autoregressive models that depend on the nonconstancy of variance models. Hybrid ARMA-GARCH models eliminate the weaknesses and gaps that exist in each group of models (ARMA and GARCH) separately, which increases their forecasting accuracy and reliability, so they have already been successfully applied to model and forecast daily stock returns for three standard indices in the USA. The purpose of this article is to investigate which of the hybrid ARMA-GARCH models is optimal for forecasting the return of the DAX index, which is the most important stock index of the German securities market. It is the German equivalent of the American Dow Jones Index, has been calculated since 1988 by Deutsche Börse AG and reflects the total return on capital of the largest stock companies listed on the Frankfurt Stock Exchange (currently 40; by 2021 – 30): calculated as a weighted average of capitalization of the value of Free Float share prices on the Xetra electronic exchange, and also takes into account dividends on shares, assuming that the dividend is reinvested in the share on which it was accrued. The database of this study consisted of the daily closing prices of the DAX index presented on the official website of the Frankfurt Stock Exchange during the period from 01.01.2018 to 09.30.2023 (altogether about 1,500 observations), the stability of the time series was assessed using Expanded Dickey Fuller Liquidity (ADF). The article proposes 7 hybrid models, from which the one that is best suited for modeling the volatility of the DAX index is selected. It is an ARMA (2,3)-EGARCH (1,1) model because it captures volatility and leverage effects on DAX returns and its expected returns more than other models. The selection of the best alternative from the developed array of hybrid models was carried out according to the following criteria: AIC (Akaike Information Criterion), BIC (Bayesian Information Criterion), H-QIC (Hannan-Quinn Information Criterion).

Diversification, hedging, and safe-haven characteristics of cryptocurrencies: A structural change approach

This study investigates the influence of structural change on the diversification, hedging, and safe-haven characteristics of Bitcoin and Ethereum against various financial assets such as gold, the US Dollar Index, stock indices, oil, and commodity indices from August 7, 2015, to August 15, 2022, using the DCC–ARMA–GARCH models with the CUSUM test. Our results indicate that cryptocurrencies have the same characteristics vis-à-vis financial markets during the entire sample period and periods tied to the date of major international events (COVID-19 and the early-2022 Russia–Ukraine War). However, we find that cryptocurrencies play different roles against specific asset markets in different periods separated by structural change models. Our findings suggest that incorporating structural changes into a model accounts for higher volatility and may better describe the real-world capabilities of cryptocurrencies against financial assets.

Dynamic Return Scenario Generation Approach for Large-Scale Portfolio Optimisation Framework

AbstractIn this paper, we propose a complex return scenario generation process that can be incorporated into portfolio selection problems. In particular, we assume that returns follow the ARMA–GARCH model with stable-distributed and skewed t-copula dependent residuals. Since the portfolio selection problem is large-scale, we apply the multifactor model with a parametric regression and a nonparametric regression approaches to reduce the complexity of the problem. To do this, the recently proposed trend-dependent correlation matrix is used to obtain the main factors of the asset dependency structure by applying principal component analysis (PCA). However, when a few main factors are assumed, the obtained residuals of the returns still explain a non-negligible part of the portfolio variability. Therefore, we propose the application of a novel approach involving a second PCA to the Pearson correlation to obtain additional factors of residual components leading to the refinement of the final prediction. Future return scenarios are predicted using Monte Carlo simulations. Finally, the impact of the proposed approaches on the portfolio selection problem is evaluated in an empirical analysis of the application of a classical mean–variance model to a dynamic dataset of stock returns from the US market. The results show that the proposed scenario generation approach with nonparametric regression outperforms the traditional approach for out-of-sample portfolios.

Forecasting Volatility of OPEC Oil Prices Using EGARCH and ARMA-GARCH Models

Some time series are characterized by their great volatility over time, especially time series related to the movement of the economy, and those related to the change in stock prices or the movement of financial transactions and stock markets, which are characterized by being non- stationary over time due to the change in the behavior of observations, making them suffer from the problem of Heteroscedasticity . The paper aims to building the best model to predict the future fluctuations in the daily OPEC oil price by applying different number of conditional autoregressive Heteroscedasticity models such as GARCH , EGARCH and ARMA-GARCH models , when errors follow Student's-t distribution, the results shows that the best model for predicting OPEC oil prices fluctuations is EGARCH(1,1), based on the AIC, SIC, and H-QIC.

Spillovers in the U.S.-China Stock Markets - A Study of Returns and Volatility under Full Sample Periods and Multi-Special Periods

This paper adopts the ARMA-GARCH model and selects the S&P500 and the SSEC to study the return rate and volatility spillover effect of the US stock market(USM) and the Chinese stock market(CSM) in the full sample period, the Chinese stock market crash in 2015 and the duration when coronavirus spread. In both the full sample period and the two specific periods, it is discovered that the USM significantly increases the return on the CSM. While the CSM barely has any impact on the USM. Although the impact is favorable over the whole sample, it is less pronounced during the The pandemic caused by the novel coronavirus and the China's 2015 stock market debacle. In the whole sample, the S&P500 is unaffected by the SSEC's volatility, whereas the SSEC is significantly harmed by the S&P500's volatility. The S&P500's volatility will have a major beneficial influence on the SSEC, but it won't be communicated from the SSEC to the S&P500 during the global spread of COVID-19. Both of the fluctuation transmission to each other were negligible during the 2015 stock market turmoil. For risk management and stock asset allocation, this study can offer important information to financial institutions, everyday individuals, and governments.

Study on the Efficiency of China's Convertible Bond Market Based on ARMA-GARCH Models

This study examines the prediction and analysis of China's convertible bond market using a combined ARMA and Generalized GARCH model. If this model can effectively achieve its predictive goals, it indirectly suggests that China's convertible bond market has not yet reached weak-form efficiency. The study focuses on the Shenzhen Investment Grade Convertible Bond Index, utilizing daily closing price data from January 2, 2019, to June 18, 2024, as the sample, providing a robust empirical foundation for the model. Empirical results indicate that the constructed model effectively captures the volatility patterns of current convertible bond yields, implying that historical price data holds certain predictive significance for current prices. Furthermore, through empirical analysis using the GARCH-M(1, 1) model, we find a relationship between yield volatility in the convertible bond market and historical risk levels. This suggests that market risk may not be fully priced rationally, as historical risk levels can help forecast current yield volatility, further confirming that China's convertible bond market has not yet achieved weak-form efficiency

The Impact of Natural Disaster on US Stock Market Index: Using DID, ARMAX-GARCH, and Random Forest

The stock market might be impacted by natural disasters, which can cause significant market disruptions and financial uncertainty, as already shown in several existing studies. This study investigates the role of natural disasters in stock market movements in the US specifically, hypothesizing that incorporating natural disasters leads to more accurate stock market predictions. Various models, including Difference-in-Differences (DID), ARMA-GARCH/ARMAX-GARCH, and Random Forest, are employed to analyze the S&P 500 index's daily returns and the impact of natural disasters. The study reveals that the ARMA-GARCH model effectively captures market volatility but does not account for all influencing factors such as interest rate, inflation rate, and natural disasters. The DID method isolates natural disaster effects, showing significant but inconsistent impacts. The Random Forest model, incorporating a disaster severity index, yields more accurate predictions than the one without, reinforcing the hypothesis and supporting previous studies. Although the study highlights the importance of considering natural disasters in stock market predictions, it also underscores the market's complexity, indicating that more features and factors should be considered in future research.

The Impact of Federal Reserve Interest Rate Hike on the Entertainment Industry: An Empirical Evidence

The purpose of this paper is to investigate the impact of Federal Reserve interest rate hikes on the entertainment industry, with a focus on the American film company Disney. The study utilizes a VAR model for impulse response analysis and an ARMA-GARCH model for assessing stock returns and conditional variances. The findings indicate that a rise in the USD index leads to a decrease in Disney's earnings from foreign markets, and a Fed rate hike could have a negative impact on its profitability. However, higher interest rates can encourage funds to flow into the stock market and increase the demand for stocks, leading to a rise in stock prices. Negative effect dominates at the beginning, followed by positive effect, and then changes back to negative effect, gradually net effect tends to 0 over time. The paper suggests that investors diversify their portfolio, and that enterprises develop targeted risk management and seek policy support. The study provides insights into the multifaceted effects of a Fed rate hike on the entertainment industry, and contributes to the existing literature on exchange rate risk and capital structure in multinational corporations.

Average and Risk-Return Analysis of Cryptocurrencies Using ARMA-GARCH Models

Cryptocurrency is a digital currency that is created through encrypted cryptography with complex algorithm and connected to each other on the blockchain system. Cryptocurrencies are widely used as investment instruments for financial assets like stocks. Similar to stocks, cryptocurrencies have a high risk – high returns characteristic, but the fluctuation of cryptocurrencies are more dynamic. Professional investors would do a volatility analysis of cryptocurrencies that potentially give the best returns. Returns assessment usually refers to the average value or expected return, while the estimated investment risk can be seen and analyzed from the volatility value. The study aimed to analyze the average and volatility of cryptocurrencies. This research was a case study done on five cryptocurrencies that are included at Top Gainers of 30 days update lists, in September 2022. The period is January 1, 2019 – September 30, 2022. The ARMA-GARCH models using three types of GARCH models, those are SGARCH(1,1), IGARCH(1,1), and TGARCH(1,1) were used for analysis. Based on the results of this research, the best ARMA-GARCH model for cryptocurrency Quant, XRP, Stellar, Monero, and Decred is ARMA(1,0)-SGARCH(1,1), ARMA(32,0)-TGARCH(1,1), ARMA(0,14)-SGARCH(1,1), ARMA(1,4)-TGARCH(1,1), and ARMA(1,0)-SGARCH(1,1). Best expected return with the lowest volatility value is owned by Monero (XMR). The research can be used by investors as a consideration in investing decision-making to cryptocurrencies.

Study on the Influence of Cotton Option Launch on The Price Fluctuation of Underlying Futures

This paper takes cotton options as the research object, and empirically tests the impact of cotton options on the price fluctuation of the underlying futures in the short and medium term by establishing the ARMA-GARCH model with the introduction of two dummy variables. The study found that the launch of cotton options increased the volatility of the underlying futures price in the short term, and increased the volatility in the medium and long term. After the launch of cotton options, the supply of national policies against the epidemic played a certain stabilizing role in the volatility of futures prices, but the policy effect has a time lag. Based on this, institutional investors should be encouraged to use cotton options and futures risk management, build a risk prevention and control mechanism for sudden public crisis events, popularize the knowledge of options and futures, and improve the transparency of cotton trading.

The Effect of Rise of Federal Funds Rate on US Stock Market: From the Perspective of US Dollar Appreciation

The study examines the impact of the rise of the Federal Funds Rate (FFR) on the stock price returns and volatility of the United States of America. The study extracted the stock price from January 3, 2022, to June 16, 2023, from the Investing finance terminal, including the Standard and Poors (S&P 500), US Dollar Index, and the National Association of Securities Dealers Automated Quotations (NASDAQ) Index. This study uses the Vector Autoregression (VAR) model and the ARMA-GARCH model to evaluate the stock returns and daily return volatility, respectively. The two models inspect the effect of the US Dollar index on both the NASDAQ and S&P 500. The result of this study suggests that the rise in the Federal Funds Rate would cause the stock market price to decline for a relatively long period. However, the volatility of the daily return remains stable. By studying the effect of the rise in the Federal Funds Rate, policymakers can change the stock prices by adjusting the Federal Funds Rate based on the markets needs.

Probabilistic forecast-based portfolio optimization of electricity demand at low aggregation levels

In the effort to achieve carbon neutrality through a decentralized electricity market, accurate short-term load forecasting at low aggregation levels has become increasingly crucial for various market participants' strategies. Accurate probabilistic forecasts at low aggregation levels can improve peer-to-peer energy sharing, demand response, and the operation of reliable distribution networks. However, these applications require not only probabilistic demand forecasts, which involve quantification of the forecast uncertainty, but also determining which consumers to include in the aggregation to meet electricity supply at the forecast lead time. While research papers have been proposed on the supply side, no similar research has been conducted on the demand side. This paper presents a method for creating a portfolio that optimally aggregates demand for a given energy demand, minimizing forecast inaccuracy of overall low-level aggregation. Using probabilistic load forecasts produced by either ARMA-GARCH models or kernel density estimation (KDE), we propose three approaches to creating a portfolio of residential households' demand: Forecast Validated, Seasonal Residual, and Seasonal Similarity. An evaluation of probabilistic load forecasts demonstrates that all three approaches enhance the accuracy of forecasts produced by random portfolios, with the Seasonal Residual approach for Korea and Ireland outperforming the others in terms of accuracy and computational efficiency.