Modeling and forecasting crude oil markets using ARCH-type models

This paper estimates the volatility of the won-dollar exchange rate during the 2008-9 crisis. We find that the volatility increased in September 2008 and decreased in May 2009. The volatility rose gradually for one month and subdued in a similar manner, which implies that the volatility was not governed by any specific event or government policy. The overall changes in the volatility are similar to the movements of the CDS premium. We also find that the UK foreign exchange market experienced a similar pattern of volatility shifts and suffered smaller but longer volatility than the Korean one. The volatility shifts are estimated using a Markov switching GARCH model and a Bayesian method is suggested.Keywords: Bayesian Inference, Markov Switching GARCH Models, Exchange Rate Volatility, Credit CrisisJEL classification: C11, C22, F31(ProQuest: ... denotes formulae omitted.)1. INTRODUCTIONThe Korean foreign exchange market has experienced two crises during the last two decades, as shown in Figure 1. The exchange rate was managed by the government before the Asian financial crisis in 1997-8. The Korean currency, or the won, depreciated sharply during the crisis and showed a trend of appreciating during the next decade. The foreign exchange market suffered from another foreign capital flight during the global credit crisis in 2008-9. Contrary to the case of the 1997-8 crisis, the 2008-9 credit crisis stemmed from the developed economies. However, the credit crisis led many developing countries, including South Korea, to an economic or financial crisis. Many policies were implemented to stabilize the financial and foreign exchange markets in Korea. The Bank of Korea has swiftly lowered the policy rate from 5.25% to 2% for 4 months since October 2008. The government announced the Financial Market Stabilization Measures, which included government warrants of the foreign currency debt of the commercial banks and provision of dollar liquidity to them, on October 19, 2008. The Bank of Korea has also made a 30-billion US dollar swap arrangement with the Federal Reserve on October 30, 2008 and other deals with the People's Bank of China and the Bank of Japan on December 12, 2008. From October 2008 to February 2009, it provided around 30-billion dollar liquidity to financial institutions which had difficulties in overseas fund raising.This paper estimates the volatility of the won-dollar exchange rate during the 2008-9 crisis and investigates what determined the volatility. We find that the volatility increased in September 2008 and decreased in May 2009. The volatility rose gradually for one month and subdued in a similar manner, which suggests that the volatility was not governed by any specific event or government policy. The overall changes in the volatility are similar to the movements of the CDS premium. We also find that the dollar-pound exchange rate experienced a similar pattern of volatility shifts to that of the won-dollar exchange rate. But, the UK foreign exchange market suffered smaller but longer volatility than the Korean one.Since the Autoregressive Conditional Heteroskedastic (ARCH) model was suggested by Engle (1982), the conditional heteroskedastic models have been updated and developed to analyze the volatility of the financial markets. Researchers, including Bollerslev (1986), generalized the ARCH model to GARCH (generalized ARCH) and its variants, such as IGARCH, GARCH-M, and EGARCH. The models are known to describe well the many features of volatility, such as volatility clustering and the leverage effect.1 However, as Schwert (1990) and Engle and Mustaffa (1992) show, the GARCH models imply too much persistence in the conditional variance. To overcome this shortcoming, Cai (1994) and Hamilton and Susmel (1994) incorporate the Markov switching component into the ARCH model. Gray (1996) and Dueker (1997) generalize their model to Markov switching GARCH (hereafter, MS-GARCH) models. …

Crude oil is an important energy commodity to mankind. The fluctuation of crude oil prices has affected many related sectors and stock market indices. Hence, forecasting the crude oil prices is essential to avoid the future prices of the non-renewable natural resources to raise sky-rocket. In this study, daily West Texas Intermediate (WTI) crude oil prices data is obtained from Energy Information Administration (EIA) from 2nd January 1986 to 30th September 2009. This study uses the Box-Jenkins methodology and Generalized Autoregressive Conditional Heteroscedasticity (GARCH) approach in analyzing the crude oil prices. ARIMA(1,2,1) and GARCH(1,1) are found to be the appropriate models under model identification, parameter estimation, diagnostic checking and forecasting future prices. In this study, the analyses are done with the aid of EViews software where the potential of this software in forecasting daily crude oil prices time series data is explored. Finally, using several measures, comparison performances between ARIMA(1, 2, 1) and GARCH(1,1) models are made. GARCH(1,1) is found to be a better model than ARIMA(1, 2, 1) model. Based on the study, it is concluded that ARIMA(1,2,1) model is able to produce good forecast based on a description of history patterns in crude oil prices. However, the GARCH(1,1) is the better model for daily crude oil prices due to its ability to capture the volatility by the non-constant of conditional variance.

Global commodity markets, particularly crude oil markets, are inherently characterized by pronounced price volatility driven by geopolitical tensions, macroeconomic shocks, financial speculation, and structural changes in energy demand and supply.Accurately modeling and forecasting such volatility is essential for policymakers, investors, and risk managers seeking to design effective stabilization, hedging, and investment strategies.This study provides a comprehensive empirical investigation of oil price volatility by applying three prominent members of the Generalized Autoregressive Conditional Heteroskedasticity (GARCH) family-namely the standard GARCH, Threshold GARCH (TGARCH), and Exponential GARCH (EGARCH) models-to monthly West Texas Intermediate (WTI) crude oil prices over the period from January 2008 to June 2024.The selected timeframe captures multiple episodes of extreme market turbulence, including the global financial crisis, oil price collapses, the COVID-19 pandemic, and recent geopolitical disruptions.The analysis proceeds through a structured econometric methodology, beginning with the transformation of price levels into return series, followed by stationarity testing, descriptive statistical analysis, and volatility modeling.Empirical results reveal strong volatility clustering and persistence in WTI oil returns, confirming the suitability of GARCH-type models for capturing oil price dynamics.While asymmetric specifications (TGARCH and EGARCH) provide valuable insights into the differential effects of positive and negative shocks, the findings indicate that the GARCH(1,1) model offers the most 207 -www.imcra.az.org,

Steel structures such as transmission towers may have cracks and other damages during the service period. When the structure vibrates, the cracks will open and close, which makes the structure have nonlinear characteristics of variant stiffness. In order to identify this type of nonlinear damage, a time-domain damage identification method based on the residual deviation distance (RDD) of the autoregressive conditional heteroskedasticity (ARCH) model is proposed. First, the basic theory of the ARCH model is introduced, and the methods of model order determination and parameter estimation are given. Then, the time-domain nonlinear damage characteristics are analyzed, and the second-order variance (SOV) index based on the ARCH model is introduced. Considering that both the ARCH model coefficient and the RDD contain nonlinear information, a conversion index is constructed using the Euclidean distance (ED) of the ARCH model coefficients before and after the damage. On this basis, an RDD conversion index is further proposed to improve the identification accuracy. Finally, a three-storey frame experiment and a complex transmission tower model experiment are used to verify the effectiveness of the proposed method. The experimental results show that the proposed RDD conversion index can better identify the location of structural damage, and the identification results of the RDD conversion index are obviously better than those of the SOV conversion index and the ED conversion index.

For the limitations of vibration signals caused by non-stationary autoregressive (AR) model which can not effectively describe the signal characteristics, it is presented a fault diagnosis based on autoregressive conditional heteroskedasticity (ARCH) model. This method firstly uses ARCH model to fit various fault signals and regard the proceeds of the model parameters as the characteristics of fault diagnosis, using RBF neural network classification as fault diagnosis method. The experimental results verify the feasibility and effectiveness of the ARCH model, and at the same time it makes the comparison with the method based on same AR model and another modified method based on AR model. The results show that the method has significantly improvements in the diagnosis rate.

This current study explores the application of Generalized Autoregressive Conditional Heteroskedasticity (GARCH) models to forecast and model crude oil price volatility. Crude oil is a vital commodity whose price fluctuations significantly impact global economies, energy markets, and strategic decisions of both National Oil Companies (NOCs) and International Oil Corporations (IOCs). Using the GARCH(1,1) and GARCH(1,2) models, this study evaluates the effectiveness of these models in capturing the dynamic nature of oil price volatility. The findings indicate that while both models fit the data well, the GARCH(1,1) model is preferred due to its parsimonious nature and comparable forecast accuracy. Despite including an additional lag in the GARCH(1,2) model, it did not significantly outperform the GARCH(1,1) model in predictive performance. The study further analyzes the residuals and autocorrelation characteristics, highlighting the potential for model refinement. The study underscores the importance of selecting an appropriate model complexity, incorporating external factors, and exploring advanced methodologies to enhance forecast accuracy. These insights are critical for developing effective risk management strategies and informing policy decisions in volatile crude oil markets.

This paper attempts to model and forecast the sugar prices volatility in the India using Generalized Autoregressive Conditional Heteroskedasticity (GARCH) models. Various types of GARCH models for instance; GARCH (1, 1), EGARCH(1, 1)were applied to sugar the period 1995–2015; to test the hypothesis of persistence, asymmetry and volatility of the spot and futuresprices. It is found that, the sum of ARCH and GARCH coefficients is not close to one, indicating that volatility shocks is not quite persistent, moreover volatility, in addition none of sugar spot and futures prices has an impact of bad news on the price volatility, while lastly leverage effect is not present on the conditional variance. Therefore (GARCH) models are appropriate in modeling and forecasting sugar prices volatility.

Gear wear is inevitable during the service life of gearboxes and may lead to catastrophic failure. As an important micro-level wear feature, tooth surface roughness directly affects the gear wear progression (lubrication regimes, wear mechanisms and wear rates) and lifespan of a gearbox. Therefore, it is important to monitor surface roughness changes. The tooth surface roughness induces random vibration signals with cyclic amplitude modulation. Reported works used an indicator of second-order cyclostationarity (ICS2) to assess such signals. However, the ICS2 gives a poor correlation with surface roughness. This paper presents the use of an Autoregressive Conditional Heteroskedasticity (ARCH) model to represent the random vibration signals with cyclic amplitude modulation. ARCH model parameter serves as an indicator to assess the changes in gear tooth surface roughness. A laboratory dataset was used to validate the effectiveness of the ARCH model in assessing surface roughness level. Results have shown that using the ARCH model returns a more accurate assessment result than the ICS2.

The impact of changes in government policies on economic performance (the ARCH model)

Portfolio Performance of the SDR and Reserve Currencies: Tests Using the Arch Methodology

This research aims to forecast fluctuations in the price of West Texas Intermediate (WTI) crude oil within the potential threat of World War III by utilizing the Generalized Autoregressive Conditional Heteroscedasticity (GARCH) method. Using daily closing price data of WTI crude oil from January 2022 to March 2025, consisting of 850 observations, this study employs the ARIMA-GARCH model to capture the patterns and volatility of the time series data. Based on the conducted analysis, it is concluded that the ARIMA (2,1,2) and GARCH (1,1) models demonstrate optimal performance, with a MAPE value of 13.71%, indicating a good prediction accuracy level. The forecast for the next two years shows a trend of price increases starting from Q2 2025 through Q4 2027. This research demonstrates how geopolitical tensions, particularly the Russia-Ukraine war and Middle Eastern Conflicts, can affect global oil price volatility while highlighting the GARCH model’s effectiveness in capturing heteroskedasticity in highly fluctuating financial data.

Bandung Regency located in West Java Province, Indonesia, has a tropical climate with high rainfall variation. This variable rainfall pattern is one of the main characteristics of tropical regions, where seasonal changes such as the rainy and dry seasons significantly impact annual rainfall patterns. In addition, high rainfall is often a trigger for natural disasters, such as floods and landslides, which can cause economic and social losses. Therefore, the ability to predict rainfall accurately is crucial, both for disaster risk mitigation and as a basis for decision-making in various sectors. This study aims to predict rainfall in Bandung Regency for the next year using a time series model approach, specifically a heteroscedastic model. The main focus of the study is to examine rainfall returns, or changes in rainfall over time while considering the nature of heteroscedasticity. In this condition, the variance of the data is not constant over time. The phenomenon of heteroscedasticity is common in rainfall data due to significant changes between seasons or extreme weather events. The study results indicate that the best model for predicting rainfall imbal hasil s is the Autoregressive Conditional Heteroskedasticity (ARCH) model. The selection of this model is based on the Akaike Information Criterion (AIC), which shows that the ARCH model outperforms the GARCH(1,1) model in handling variance instability in rainfall data. The advantage of the ARCH model lies in its ability to dynamically model variance instability, resulting in more accurate predictions. This model is not only capable of capturing high volatility patterns but also provides a more realistic estimate of large fluctuations that could occur in the future.

An important development in the modelling of exchange rate volatility is the use of artificial neural networks (ANN) to create enhanced generalised autoregressive conditional heteroskedasticity (GARCH) models. Conventional GARCH models are good at capturing the clustering of volatility in financial time series, but they have trouble understanding complex linkages and non-linear patterns in the data. This paper aims to investigate the hybrid approach in modelling exchange rate volatility of two currency pairs: South African Rand against Brazilian Real (ZAR/REAL) and South African Rand against Chinese Yuan (ZAR/YUAN) using monthly observations over the period of January 1996-March 2024. The paper introduced ANN as an additional factor to both symmetric and asymmetric GARCH models that capture most common stylised facts about exchange rate volatility and leverage effects. The GARCH (1,1)-ANN, EGARCH (1,1)-ANN, and GJR-GARCH (1,1)-ANN models were used, and their performance was assessed using mean squared error (MSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). The results revealed that the EGARCH (1,1)-ANN model had the best overall performance when compared to the other hybrid models based on all three evaluation measures for both the currency pairs’ data. The paper recommends further similar studies to predict future exchange rate trends and also incorporating other nonlinear methods.

This paper extends the call option model of Milonas and Thomadakis (1997) to estimate oil convenience yields with futures prices. We define the business cycle of a seasonal commodity with demand/supply shocks and find that the convenience yield for crude oil exhibits seasonal behavior. The convenience yield for West Texas Intermediate (WTI) crude oil is the highest in the summer, while that for Brent crude oil is the highest in the winter. This implies that WTI crude oil is more sensitive to high summer demand and that Brent crude oil is more sensitive to shortages in winter supply. Convenience yields are negatively related to the inventory level of the underlying crude oil and positively related to interest rates due to the business cycle. We also show that convenience yields may explain price spread between WTI crude oil and Brent crude oil. Our computed convenience yields are consistent with Fama and French (1988) in that oil prices are more volatile than futures prices at low inventory level, verifying the Samuelson (1965) hypothesis that future prices are less variables than spot prices at lower inventory levels.

PurposeThis study aims to investigate the conditional volatility of the Asian stock market concerning Bitcoin and global crude oil price movement.Design/methodology/approachThis study uses the newest Dynamic Conditional Correlation (DCC)-Generalized Autoregressive Conditional Heteroskedasticity (GARCH) model to examine the conditional volatility of the stock market for Bitcoin and crude oil prices in the Asian perspective. The sample stock market includes Chinese, Indian, Japanese, Malaysian, Pakistani, Singaporean, South Korean and Turkish stock exchanges, with daily time series data ranging from 4 April 2015−31 July 2023.FindingsThe outcome reveals the presence of volatility clustering on the return series of crude oil, Bitcoin and all selected stock exchanges of the current study. Secondly, the outcome of DCC, manifests that there is no short-run volatility spillover from crude oil to the Malaysian, Pakistani and South Korean and Turkish stock markets, whereas Chinese, Indian, Japanese, Singapore stock exchanges show the short-run volatility spillover from crude oil in the short run. On the other hand, in the long run, there is a volatility spillover effect from crude oil to all the stock exchanges. Thirdly, the findings suggest that there is no immediate spillover of volatility from Bitcoin to the stock markets return volatility of China, India, Malaysia, Pakistan, South Korea and Singapore. In contrast, both the Japanese and Turkish stock exchanges exhibit a short-term volatility spillover from Bitcoin. In the long term, a volatility spillover effect from Bitcoin is observed in all stock exchanges except for Malaysia. Lastly, based on the outcome of conditional variance, it can be concluded that there was increase in the return volatility of stock exchanges during the period of the COVID-19 pandemic.Research limitations/implicationsThe analysis below does not account for the bias induced due to certain small sample properties of DCC-GARCH model. There exists a huge literature that suggests other methodologies for small sample corrections such as the DCC connectedness approach. On the other hand, decisive corollaries of the conclusions drawn above have been made purely based on a comprehensive investigation of eight Asian stock exchange economies. However, there is scope for inclusive examination by considering other Nordic and Western financial markets with panel data approach to get more robust inferences about the reality.Originality/valueMost of the empirical analysis in this perspective skewed towards the Nordic and Western countries. In addition to that many empirical investigations examine either the impact of crude oil price movement or Bitcoin performance on the stock market return volatility. However, none of the examinations quests the crude oil and Bitcoin together to unearth their implication on the stock market return volatility in a single study, especially in the Asian context. Hence, current investigation endeavours to examine the ramifications of Bitcoin and crude oil price movement on the stock market return volatility from an Asian perspective, which has significant implications for the investors of the Asian financial market.