Volatility and Time Series Econometrics
... The financial econometric volatility is silent upon links between asset return volatility and its determinants. Instead, the focus is on modeling volatility and not underlying macroeconomic factors (Bollerslev et al., 2010)Volatility is one of the important quantities for an investor and any economic and financial theory is dependent upon it.(Park & Linton, 2012)asymmetry in volatility is rare in emerging and frontier markets; asymmetry in correlations concerns the Hungarian stock market; and the relationship between volatility and correlations is positive and significant in the majorityof countries. ...
... The GARCH model is an extension of the ARCH (Autoregressive Conditional Heteroskedastic) process, allowing for a more flexible lag structure to capture changing variance over time which is essential for modeling time series exhibiting long memory. (Bollerslev et al., 2010)The t-distributed statistics of standardized returns generally lead to a better average performance than the Gaussian. (Hansen & Lunde, 2005)To address the limitations of ARCH models, particularly the potential for negative variance estimates, Bollerslev (1986) and Taylor (1986) proposed a more parsimonious alternative: the Generalized ARCH (GARCH) model. ...
... The financial econometric volatility is silent upon links between asset return volatility and its determinants. Instead, the focus is on modeling volatility and not underlying macroeconomic factors (Bollerslev et al., 2010)Volatility is one of the important quantities for an investor and any economic and financial theory is dependent upon it.(Park & Linton, 2012)asymmetry in volatility is rare in emerging and frontier markets; asymmetry in correlations concerns the Hungarian stock market; and the relationship between volatility and correlations is positive and significant in the majorityof countries. ...
... The GARCH model is an extension of the ARCH (Autoregressive Conditional Heteroskedastic) process, allowing for a more flexible lag structure to capture changing variance over time which is essential for modeling time series exhibiting long memory. (Bollerslev et al., 2010)The t-distributed statistics of standardized returns generally lead to a better average performance than the Gaussian. (Hansen & Lunde, 2005)To address the limitations of ARCH models, particularly the potential for negative variance estimates, Bollerslev (1986) and Taylor (1986) proposed a more parsimonious alternative: the Generalized ARCH (GARCH) model. ...
The study was conducted on BUX Index volatility for the post-2008 (from 2011) global financial crisis period using advanced GARCH models (GARCH, TGARCH, EGARCH, IGARCH, PARCH, APARCH). Based on parameters and test results appropriate model was chosen (APARCH (1,1) at Student’s t distribution) to study volatility, the presence of asymmetry, leverage effect, volatility clustering, and decay factor. Test results were linked with the macro and microenvironment (Political instability, Geopolitical crisis, Unemployment, Inflation, COVID-19, Slowdown, etc.) of the index and unique features of the index have been discovered (Like a sudden huge dip between 2020-2022). The study through mathematical
and econometrics terms establishes causal links among the variables affecting the index. The paper is relevant to both investors and policymakers as BUX is one of the most important indicators as far as stock market in Hungary is concerned.
... Therefore, the conditional variance is affected by both past values of residuals and conditional variance values. Bollerslev (2010) provide an easy-to-use encyclopedictype reference guide to the long list of ARCH acronyms. Although he has listed well over 100 variants of the original model, the GARCH model extensions are defined utilizing Hentschel's approach in "rugarch" R-package of Ghalanos (2020a;2020b) in this paper. ...
The aim of the study is to determine the most appropriate discrete model for the volatility of Bitcoin returns using the discrete-time GARCH model and its extensions and compare it with the Lévy-driven continuous-time GARCH model. For this purpose, the volatility of Bitcoin returns is modeled using daily data of the Bitcoin / United States Dollar exchange rate. By comparing discrete-time models according to information criteria and likelihood values, the All-GARCH model with Johnson's-SU innovations is found as the most adequate model. The persistence of the volatility and half-life of the volatility of the returns are calculated according to the estimation of the discrete model. This discrete model has been compared with the continuous model in which the Lévy increments are derived from the compound Poisson process using various error measurements. In conclusion, it is found that the continuous-time GARCH model shows a better performance in predicting volatility.
The literature regarding innovation drivers is usually based on variables taken from some theoretical approach and validated within a methodology. Some authors have included COVID-19 as a driver for innovations. In this paper, we address the pandemic from a different viewpoint: trying to find if innovation drivers for European countries are the same in pre- and post-pandemic years. The automated general-to-specific model selection algorithm—Autometrics—is used. The main potentially relevant drivers for which data were available for both years and two proxies of innovation (patents and the Summary Innovation Index) were considered. The final models provided by Autometrics allow for valid inference on retained innovation drivers since they have passed a plethora of diagnostic tests, ensuring congruency. The attractiveness of the research system is the most impactful driver on the index in both years but other drivers indeed differ. SMEs’ business process innovation and their cooperation networks matter only in 2022. We found crowding-out effects of public funding of R&D (in both years, for the index). Sustainability was a driver in both periods. The ranking of common drivers also changes. Non-R&D innovation expenditures, the second most relevant before COVID-19, concedes to digitalization. Surprisingly, when patents are the proxy, digitalization is retained before COVID-19, with the attractiveness of the research system replacing it afterwards. Explanations for our findings are suggested. The main implications of our findings for innovation policy seem to be the facilitating role that the government should have in fostering linkages between stakeholders and the capacity the government might have to improve the attractiveness of the research system. Policies based on the public funding of R&D appear ineffective for European countries.
This study examines the response of real stock returns to expected inflation and uncertainty as measured by state variable correlated with equity market volatility (EMV). Evidence reveals a significantly negative relationship between real stock returns and expected inflation for each country except some cases in India and Japan. Evidence indicates a negative relationship between real stock returns and uncertainty, which is measured not only by the impact of the Fed’s monetary policy uncertainty but also from various state variables that covary with EMV. These elements have not been explicitly incorporated into test equations in previous studies of the inflation-stock return relationship. The model is robust in its ability to test data for both advanced and emerging markets, level or the first difference of explanatory variables, and various categorical EMVs. Evidence shows that the Fed’s rate hikes respond to the inflation data, displaying a nonlinear impact on real stock returns.
Se estudiaron las dinámicas y volatilidades de seis series derendimientos cambiarios asiáticos durante y después de la pandemia de COVID-19. El estudio emplea siete modelos ARCH/GARCH, diversos supuestos estadísticos y tres criterios de bondad de ajuste. Los hallazgos indican que los modelos más adecuados para describir las series de rendimientos cambiarios, son: 1) el FIEGARCH(1,1,1) para los rendimientos de China, Indonesia y Japón; 2) el FIGARCH(1,1) para Malasia; 3) el GARCH(1,1) para Hong Kong; y 4) el PARCH(1,1,1) para Taiwán. Las seis series de tipos de cambio utilizadas incluyen datos diarios desde el 2 de enero de 2020 hasta el 15 de febrero de 2024.
Widely used volatility forecasting methods are usually based on low‐frequency time series models. Although some of them employ high‐frequency observations, these intraday data are often summarized into low‐frequency point statistics, for example, daily realized measures, before being incorporated into a forecasting model. This paper contributes to the volatility forecasting literature by instead predicting the next‐period intraday volatility curve via a functional time series forecasting approach. Asymptotic theory related to the estimation of latent volatility curves via functional principal analysis is formally established, laying a solid theoretical foundation of the proposed forecasting method. In contrast with nonfunctional methods, the proposed functional approach fully exploits the rich intraday information and hence leads to more accurate volatility forecasts. This is confirmed by extensive comparisons between the proposed method and those widely used nonfunctional methods in both Monte Carlo simulations and an empirical study on a number of stocks and equity indices from the Chinese market.
We study the dynamics and volatilities of six East Asian stock market indices during the COVID-19 pandemic with five types of ARCH/GARCH models. The main results are: 1) Most of the volatilities of the series of returns show leverage effects; 2) the FIGARCH(1,1,1) model is the best one to describe the series of returns associated to the Shenzen and Shangai-Composite indices; 3) the GJR-GARCH(1,1,1) model is the best one to describe the series associated to the Hang-Seng, KOSPI and Nikkei-225 indices; and, 4) the APARCH(1,1,1,1) model is the best one to describe the series associated to the Taiwan-Weighted index. We develop the study with daily indices for the period between January 2nd, 2020 and December 16th, 2021.
Risk has always been central to finance, and managing risk depends critically on information. As evidenced by recent events, the need has never been greater for skills, systems and methodologies to manage risk information in financial markets. Authored by leading figures in risk management and analysis, this handbook serves as a unique and comprehensive reference for the technical, operational, regulatory and political issues in collecting, measuring and managing financial data. It will appeal to a wide range of audiences, from financial industry practitioners and regulators responsible for implementing risk management systems, to system integrators and software firms helping to improve such systems. Volume I examines the business and regulatory context that makes risk information so important. A vast set of techniques and processes have grown up over time, and without an understanding of the broader forces at work, it is all too easy to get lost in the details.
Risk has always been central to finance, and managing risk depends critically on information. As evidenced by recent events, the need has never been greater for skills, systems and methodologies to manage risk information in financial markets. Authored by leading figures in risk management and analysis, this handbook serves as a unique and comprehensive reference for the technical, operational, regulatory and political issues in collecting, measuring and managing financial data. It will appeal to a wide range of audiences, from financial industry practitioners and regulators responsible for implementing risk management systems, to system integrators and software firms helping to improve such systems. Volume I examines the business and regulatory context that makes risk information so important. A vast set of techniques and processes have grown up over time, and without an understanding of the broader forces at work, it is all too easy to get lost in the details.
Bitcoin has gradually gained acceptance as a payment method that, unlike electronic payments in dollars or euros, passes through the international trading system with zero or lower fees. Moreover, Bitcoin and e-commerce have become increasingly intertwined in recent years as cryptocurrencies gain mainstream acceptance. In this paper, we analyze Bitcoin price evolution from September 2014 until July 2023, factors that influence price volatility and assess its future volatility using Autoregressive Conditional Heteroskedasticity (ARCH) models that predict the volatility of financial returns to conceive strategies for merchants that accept Bitcoin as a payment option. The Generalized ARCH model (GARCH) extends the model to capture more persistent volatility patterns. Further, we estimate symmetric and asymmetric GARCH (1,1)-type models with normal and non-normal innovations. The best proved to be EGARCH (1,1) with t-distribution innovation. To assist merchants in making decisions regarding Bitcoin adoption, two concepts are relevant: the EGARCH model and VaR. EGARCH model is used to forecast the volatility of the financial asset, while VaR is a widely used risk management tool that estimates the potential loss in value of a portfolio over a defined period. For a merchant holding Bitcoin, VaR assists in understanding the maximum expected loss over a certain time frame with a certain level of confidence (like 95% or 99%). The results show that a VaR coverage of 0.044 at a 5% probability level suggests that there is 95% confidence that the maximum loss will not exceed 4.4% of the investment value.
The multifaceted interrelationship between petroleum prices and equity markets has been a subject of immense interest. The current paper offers an extensive review of a plethora of empirical studies in this strand of literature. By scrutinising over 190 papers published from 1983 to 2023, our survey reveals various research themes and points to diverse findings that are sector- and country-specific and contingent on employed methodologies, data frequencies, and time horizons. More precisely, petroleum price changes and shocks exert direct or indirect effects dictated by the level of petroleum dependency across sectors and the country’s position as a net petroleum exporter or importer. The interlinkages tend to display a time-varying nature and sensitivity to major market events. In addition, volatility is not solely spilled from petroleum to equity markets; it is also observed to transmit in the reverse direction. The importance of incorporating asymmetries is documented. Lastly, the summarised findings can serve as the basis for further research and reveal valuable insights to market participants.
Esta investigación presenta un estudio comparativo de los rendimientos cambiarios latinoamericanos, en el que se usó la metodología de cointegración de Johansen y los modelos asimétricos TGARCH y EGARCH. Los resultados indican que las volatilidades de los rendimientos de Argentina, Brasil, Chile y Colombia no presentan efectos asimétricos. En México y Perú las malas noticias reducen la volatilidad de los rendimientos cambiarios; además, los resultados sugieren que los rendimientos de Argentina, Brasil, Chile y Perú se describen mediante el modelo AR(1)-TGARCH(1,1); mientras que los rendimientos de Colombia y México lo hacen a través del AR(1)-EGARCH(1,1). Finalmente, se usaron rendimientos diarios para el periodo comprendido entre el 2 de enero de 2002 y el 27 de septiembre de 2011.Clasificación JEL: F31, G15, C58.
Cyber attacks are a major and routine threat to the modern society. This highlights the importance of forecasting (i.e., predicting) cyber attacks, just like weather forecasting in the real world. In this paper, we present a study on characterizing, modeling and forecasting the number of cyber attacks at an aggregate level by leveraging a high-quality, publicly-available dataset of cyber attacks against enterprise networks; the dataset is of high quality because more than 99% of the attacks were examined and confirmed by human analysts. We find that the attacks exhibit high volatilities and burstiness. These properties guide us to design statistical models to accurately forecast cyber attacksand draw useful insights.
We analyse the pattern of daily price of a collection of artistic non-fungible tokens, namely, the “Bored Ape Yacht Club” (BAYC) collectibles, over the first year of their life, from May 2021 to May 2022. Taking a time-series analysis approach, we consider the daily average price, and other variants of daily price index, derived from hedonic regression model. Aesthetic features of the collectibles do matter. At the same time, the price series emerge to be non-stationary, integrated of order 1, with their first difference exhibiting heteroscedasticity and autoregressive variance. Models of ARCH/GARCH class are appropriate to describe the dynamics. Though the price series of BAYC collectibles and their daily movements share many characteristics with the series of financial assets, they do not appear to be related to financial variables from both the crypto- and the real (i.e., not crypto) world.
This paper provides evidence regarding the relationship between asset returns and (expected) inflation in the U.S. market. Evidence indicates that inflation has a negative effect on stocks, REIT and bonds. However, its effect on housing and gold assets is positive. Evidence concludes both housing and gold tend to show a positive correlation with inflation. This study finds that inflation causes equity market volatility due to investors’ fears about the possibility of interest rate hikes by the Fed, which further aggravates the price of stocks and REIT, but helps to improve bond prices due to a flight-to-quality effect.
This study examines the impacts of the US inflation rate on the bond prices of G7 countries across different maturities using inflation-induced equity market volatility (EMV) to better account for bond price determinants. The regression model, a GED-GARCH (1,1) procedure, is adopted to deal with the volatility clustering and fat tail features in bond return estimation. The testing results indicate that the inflation rate has a negative effect on bond returns across different maturities, although an exception occurs for longer maturities in Japan. Evidence shows that US inflation has a significant impact on bond returns for the non-US G7 countries. The negative effects from US inflation are more profound than those from the domestic market (expect in Japan). This study introduces the equity market volatility arising from inflation or the Fed’s interest rate change; this variable produces market volatility that has a positive effect on bond returns, offsetting part of the original negative effect from a rise in inflation.
This paper studies a subclass of the class of generalized hyperbolic distribution called the semi-hyperbolic distribution. We obtain analytical expressions for the cumulative distribution function and, specifically, their first and second lower partial moments. Using the received formulas, we compute the value at risk, the expected shortfall, and the semivariance in the semi-hyperbolic model of the financial market. The formulas depend on the values of generalized hypergeometric functions and modified Bessel functions of the second kind. The research illustrates the possibility of analysis of generalized hyperbolic models using the same methodology as is employed for the well-established variance-gamma model.
Using the capital asset pricing model, this article critically assesses the relative importance of computing ‘realized’ betas from high-frequency returns for Bitcoin and Ethereum—the two major cryptocurrencies—against their classic counterparts using the 1-day and 5-day return-based betas. The sample includes intraday data from 15 May 2018 until 17 January 2023. The microstructure noise is present until 4 min in the BTC and ETH high-frequency data. Therefore, we opt for a conservative choice with a 60 min sampling frequency. Considering 250 trading days as a rolling-window size, we obtain rolling betas < 1 for Bitcoin and Ethereum with respect to the CRIX market index, which could enhance portfolio diversification (at the expense of maximizing returns). We flag the minimal tracking errors at the hourly and daily frequencies. The dispersion of rolling betas is higher for the weekly frequency and is concentrated towards values of β > 0.8 for BTC (β > 0.65 for ETH). The weekly frequency is thus revealed as being less precise for capturing the ‘pure’ systematic risk for Bitcoin and Ethereum. For Ethereum in particular, the availability of high-frequency data tends to produce, on average, a more reliable inference. In the age of financial data feed immediacy, our results strongly suggest to pension fund managers, hedge fund traders, and investment bankers to include ‘realized’ versions of CAPM betas in their dashboard of indicators for portfolio risk estimation. Sensitivity analyses cover jump detection in BTC/ETH high-frequency data (up to 25%). We also include several jump-robust estimators of realized volatility, where realized quadpower volatility prevails.
Risk has always been central to finance, and managing risk depends critically on information. As evidenced by recent events, the need has never been greater for skills, systems and methodologies to manage risk information in financial markets. Authored by leading figures in risk management and analysis, this handbook serves as a unique and comprehensive reference for the technical, operational, regulatory and political issues in collecting, measuring and managing financial data. It will appeal to a wide range of audiences, from financial industry practitioners and regulators responsible for implementing risk management systems, to system integrators and software firms helping to improve such systems. Volume I examines the business and regulatory context that makes risk information so important. A vast set of techniques and processes have grown up over time, and without an understanding of the broader forces at work, it is all too easy to get lost in the details.
Risk has always been central to finance, and managing risk depends critically on information. As evidenced by recent events, the need has never been greater for skills, systems and methodologies to manage risk information in financial markets. Authored by leading figures in risk management and analysis, this handbook serves as a unique and comprehensive reference for the technical, operational, regulatory and political issues in collecting, measuring and managing financial data. It will appeal to a wide range of audiences, from financial industry practitioners and regulators responsible for implementing risk management systems, to system integrators and software firms helping to improve such systems. Volume I examines the business and regulatory context that makes risk information so important. A vast set of techniques and processes have grown up over time, and without an understanding of the broader forces at work, it is all too easy to get lost in the details.
The celebrated Heston’s stochastic volatility (SV) model for the valuation of European options provides closed form solutions that are given in terms of characteristic functions. However, the numerical calibration of this five-parameter model, which is based on market option data, often remains a daunting task. In this paper, we provide a theoretical solution to the long-standing ‘open problem’ of characterizing the class of risk neutral distributions (RNDs), if any, that satisfy Heston’s SV for option valuation. We prove that the class of scale parameter distributions with mean being the forward spot price satisfies Heston’s solution. Thus, we show that any member of this class could be used for the direct risk neutral valuation of option prices under Heston’s stochastic volatility model. In fact, we also show that any RND with mean being the forward spot price that satisfies Heston’s option valuation solution must also be a member of the scale family of distributions in that mean. As particular examples, we show that under a certain re-parametrization, the one-parameter versions of the log-normal (i.e., Black–Scholes), gamma, and Weibull distributions, along with their respective inverses, are all members of this class and thus, provide explicit RNDs for direct option pricing under Heston’s SV model. We demonstrate the applicability and suitability of these explicit RNDs via exact calculations and Monte Carlo simulations, using already published index data and a calibrated Heston’s model (S&P500, ODAX), as well as an illustration based on recent option market data (AMD).
Structural breaks have attracted considerable attention recently, especially in light of the financial crisis, Great Recession, the COVID-19 pandemic, and war. While structural breaks pose significant econometric challenges, machine learning provides an incisive tool for detecting and quantifying breaks. The current paper presents a unified framework for analyzing breaks; and it implements that framework to test for and quantify changes in precipitation in Mauritania over 1919–1997. These tests detect a decline of one third in mean rainfall, starting around 1970. Because water is a scarce resource in Mauritania, this decline—with adverse consequences on food production—has potential economic and policy consequences.
Anthropogenic emissions increase the concentration of greenhouse gases, including carbon dioxide, which necessitates the promotion of environmental protection as one of the most urgent tasks of European environmental policy. The reduction of greenhouse gas emissions and the development of clean technologies in production also depends on the impact of environmental taxation; in this regard, a methodology for analyzing its impact and assessment on the development of eco-friendly technologies is proposed. An analysis of environmental tax revenues to the budgets of the EU countries revealed the insufficiency of environmental revenues to cover the costs of environmental protection from the damage caused by greenhouse gas emissions, which requires the transformation of the system of fiscal mechanisms. The total receipts of all environmental taxes in the EU budget for the period 2000–2020 increased by 53%, and the receipts from taxes on greenhouse gas emissions into the atmosphere increased by 71% in the EU budget, with a tax rate increase of 1.5-fold over this period. The application of the proposed methodology made it possible to determine, on the basis of the correlation coefficient, a high connection strength of +0.971 for the period 2000–2020 between the receipts of the environmental tax for greenhouse gas emissions into the atmosphere and the total values of all environmental taxes, as well as a fairly strong feedback of +0.913 from the receipts of the environmental tax to the EU budget with gross domestic product. Therefore, it is proposed to use differentiated environmental tax rates for different stages of the development of clean technologies.
We study recurrent patterns in volatility and volume for major cryptocurrencies, Bitcoin and Ether, using data from two centralized exchanges (CEXs; Coinbase Pro and Binance) and a decentralized exchange (DEX; Uniswap V2). We find systematic patterns in both volatility and volume across day-of-the-week, hour-of-the-day, and within the hour. These patterns have grown stronger over the years and are presumably related to algorithmic trading and funding times in futures markets. We also document that price formation mainly takes place on the CEXs while price adjustments on the DEXs can be sluggish.
Purpose
The purpose of this study is to present evidence as to whether the use of gold or silver can be justified as an asset to hedge against policy uncertainty and COVID-19 in the Chinese market.
Design/methodology/approach
By using a GARCH model with a generalized error distribution (GED), this study specifies that the gold (or silver) return is a function of a set of economic and uncertainty variables, which include volatility from interest rate innovation, a change in economic policy uncertainty (EPU), a change in geopolitical risk (GPR) and volatility due to pandemic diseases, while controlling for stock market returns, inflation rates, economic growth and the Chinese currency value.
Findings
This study employs monthly data of gold and silver prices over the period from January 2002 to August 2021 to examine hedging behavior. Estimated results show that the gold return is positively correlated to the stock return and a rise in uncertainty from economic policy innovation, geopolitical risk, volatility due to US interest rate innovation as well as COVID-19 infection. This result suggests that gold cannot be used to hedge against a stock market decline, but can be used to hedge against uncertainty in general. However, the silver return only responds positively to a rise in uncertainty from the inflation rate and geopolitical risk. Evidence shows that silver returns are negatively correlated with stock returns, and display hedging characteristics. However, the evidence lacks statistically significance during the COVID-19 period, suggesting that the role of silver as a safe-haven asset against stock market turmoil is weak for this time period.
Research limitations/implications
More general nonlinear specifications can be developed. The tests may include different measures of uncertainty that interact with each other or with the lagged error terms. An implication of the model is that gold can be used to hedge against a broad range of uncertainties for economic policy change, political risk and/or a pandemic. However, the use of gold as an asset to hedge against a stock downturn in Chinese market should be done with caution.
Practical implications
This study has important policy implications as regards a choice in assets in formatting a portfolio to hedge against uncertainty. Specifically, this study presents empirical evidence on gold and silver return behavior and finds that gold returns respond positively to heightened uncertainty. Thus, gold is a good asset to hedge against uncertainty arising from policy innovations and infectious disease uncertainty.
Social implications
This paper provides insightful information on the choice of assets toward hedging against risk in the uncertainty market conditions. It provides information to investors and policy makers to use gold price movements as a signal for detecting the arrival of uncertainty. This study also provides information for demanding a risk premium for infectious disease.
Originality/value
This study empirically analyzes and verifies the role that gold serves as a safe haven asset to hedge against uncertainty in the Chinese market. This paper contributes to the literature by presenting evidence of risk/uncertainty premiums for holding gold against various sources of uncertainty such as economic policy uncertainty, geopolitical risk and equity market volatility due to US interest rate innovation and/or COVID-19. This study finds evidence that supports the use of a nonlinear specification, which demonstrates the interaction of uncertainty with the lagged change of infectious disease and helps to explain the gold/silver return behavior. Further, evidence shows that the gold return is positively correlated to the stock return. This finding contrasts with evidence in the US market. However, silver returns are negatively correlated with stock returns, but this correlation becomes insignificant during the period of COVID-19.
We propose two sets of tests for the overall presence of outliers in regression models. First, ‘simple’ tests on whether the proportion and the number of detected outliers deviate from their expected values. Second, ‘scaling’ tests on whether the proportion of outliers decreases with the cut‐off used to detect outliers. We apply our tests to a panel difference‐in‐differences model of transport CO2 emissions in response to the introduction of North America's first major carbon tax. Our tests show the presence of significant outliers in the un‐taxed control group, which results in an overestimation of the estimated impacts of the tax.
The aim of this study is to examine the volatility spillover between bitcoin and Turkish financial markets for the pre-COVID-19 and COVID-19 periods. Using GARCH-based volatility spillover indices, the authors find that BTC-USD was a volatility transmitter in the pre-COVID-19 period but has become the main volatility receiver in the COVID-19 period, and its net volatility transmission fell from 0.7% to -10.84%. Moreover, they concluded that the total spillover index increased from 12.49% to 15.25% indicates a low connectedness between the markets in both periods and the error variance in markets is on average 15.25% originated from other markets in the COVID-19 period.
By modeling the volatility structure of banks, the characteristic structure of risks and uncertainties that concern the economy as well as banks are revealed. In this study, it is aimed to estimate the volatility of stock returns of banks in Turkey. The review period of the study is January 5, 2010 - December 31, 2020. The return volatility of banks' stocks was estimated with the nonlinear asymmetric conditional volatility analysis method (APGARCH) proposed by Ding, Granger, and Engle (1993). In the study, first of all, the stability of returns, ARCH effect, asymmetry structure, and linearity properties are tested. Then, with the APGARCH model, it was revealed that the shock in the return volatility of banks has high permanence, has an asymmetry effect and has a long-term memory feature. The findings support that the existence of Fractal Market Hypothesis rather than the Efficient Market Hypothesis in the stock return volatility of the banks in Turkey. Accordingly, dependency on stock prices has been determined. Therefore, it can be said that investors take into account the assumptions of technical analysis.
We propose a method to explore the causal transmission of an intervention through two endogenous variables of interest. We refer to the intervention as a catalyst variable. The method is based on the reduced-form system formed from the conditional distribution of the two endogenous variables given the catalyst. The method combines elements from instrumental variable analysis and Cholesky decomposition of structural vector autoregressions. We give conditions for uniqueness of the causal transmission.
We examine the problem of modeling and forecasting European Day-Ahead and Month-Ahead natural gas prices. For this, we propose two distinct probabilistic models that can be utilized in risk- and portfolio management. We use daily pricing data ranging from 2011 to 2020. Extensive descriptive data analysis shows that both time series feature heavy tails, conditional heteroscedasticity, and show asymmetric behavior in their differences. We propose state-space time series models under skewed, heavy-tailed distributions to capture all stylized facts of the data. They include the impact of autocorrelation, seasonality, risk premia, temperature, storage levels, the price of European Emission Allowances, and related fuel prices of oil, coal, and electricity. We provide rigorous model diagnostics and interpret all model components in detail. Additionally, we conduct a probabilistic forecasting study with significance tests and compare the predictive performance against literature benchmarks. The proposed Day-Ahead (Month-Ahead) model leads to a 13% (9%) reduction in out-of-sample continuous ranked probability score (CRPS) compared to the best performing benchmark model, mainly due to adequate modeling of the volatility and heavy tails.
This paper examines the impact of changes in economic policy uncertainty (EPU) and COVID-19 shock on stock returns. Tests of 16 global stock market indices, using monthly data from January 1990 to August 2021, suggest a negative relation between the stock return and a country’s EPU. Evidence suggests that a rise in the U.S. EPU causes not only a decline in a country’s stock return, but also a negative spillover effect on the global market; however, we cannot find a comparable negative effect from global EPU to U.S. stocks. Evidence suggests that the COVID-19 pandemic has a negative impact that significantly affects stock return worldwide. This study also finds an indirect COVID-19 impact that runs through a change in domestic EPU and, in turn, affects stock return. Evidence shows significant COVID-19 effects that change relative stock returns between the U.S. and global markets, creating a decoupling phenomenon.
Developments in the world of finance have led the authors to assess the adequacy of using the normal distribution assumptions alone in measuring risk. Cushioning against risk has always created a plethora of complexities and challenges; hence, this paper attempts to analyse statistical properties of various risk measures in a not normal distribution and provide a financial blueprint on how to manage risk. It is assumed that using old assumptions of normality alone in a distribution is not as accurate, which has led to the use of models that do not give accurate risk measures. Our empirical design of study firstly examined an overview of the use of returns in measuring risk and an assessment of the current financial environment. As an alternative to conventional measures, our paper employs a mosaic of risk techniques in order to ascertain the fact that there is no one universal risk measure. The next step involved looking at the current risk proxy measures adopted, such as the Gaussian-based, value at risk (VaR) measure. Furthermore, the authors analysed multiple alternative approaches that do not take into account the normality assumption, such as other variations of VaR, as well as econometric models that can be used in risk measurement and forecasting. Value at risk (VaR) is a widely used measure of financial risk, which provides a way of quantifying and managing the risk of a portfolio. Arguably, VaR represents the most important tool for evaluating market risk as one of the several threats to the global financial system. Upon carrying out an extensive literature review, a data set was applied which was composed of three main asset classes: bonds, equities and hedge funds. The first part was to determine to what extent returns are not normally distributed. After testing the hypothesis, it was found that the majority of returns are not normally distributed but instead exhibit skewness and kurtosis greater or less than three. The study then applied various VaR methods to measure risk in order to determine the most efficient ones. Different timelines were used to carry out stressed value at risks, and it was seen that during periods of crisis, the volatility of asset returns was higher. The other steps that followed examined the relationship of the variables, correlation tests and time series analysis conducted and led to the forecasting of the returns. It was noted that these methods could not be used in isolation. We adopted the use of a mosaic of all the methods from the VaR measures, which included studying the behaviour and relation of assets with each other. Furthermore, we also examined the environment as a whole, then applied forecasting models to accurately value returns; this gave a much more accurate and relevant risk measure as compared to the initial assumption of normality.
This study investigates the impact of unexpected monetary growth (UΔM) and changes in U.S. monetary policy uncertainty (ΔMPU) on international stock returns while controlling for a change in equity market volatility (ΔEMV)and dividend yield (DY). Testing of North American stock market indices consistently shows that both UΔM and ΔMPU have significant negative impacts on stock returns, which extend the effects to one month lag. Further testing of Europe, Latin America and Asia market indices yields comparable qualitative results. The evidence confirms that an increase in the U.S. MPU is transmitted to international stock markets. This finding supports the international risk/uncertainty premium hypothesis. However, a rise in U.S. unexpected monetary growth as measured by UΔM has a less consistent effect in Latin American and Asian stock markets.
In the last two decades, several methods for estimating Value at Risk have been proposed in the literature. Four of the most successful approaches are conditional autoregressive Value at Risk, extreme value theory, filtered historical simulation and time‐varying higher order conditional moments. In this paper, we compare their performances under both an empirical investigation using 80 assets and a large Monte Carlo simulation. From our analysis, we conclude that most of the methods seem not to imply huge numerical difficulties and, according to usual backtests and performance measurements, extreme value theory presents the best results most of the times, followed by filtered historical simulation.
The paper sketches and elaborates on a framework integrating agent-based modelling with advanced quantitative probabilistic methods based on copula theory. The motivation for such a framework is illustrated on a artificial market functioning with canonical asset pricing models, showing that dependencies specified by copulas can enrich agent-based models to capture both micro-macro effects (e.g. herding behaviour) and macro-level dependencies (e.g. asset price dependencies). In doing that, the paper highlights the theoretical challenges and extensions that would complete and improve the proposal as a tool for risk analysis.
The directional news impact curve (DNIC) is a relationship between returns and a probability of next period's return to exceed a certain threshold, zero in particular. Using long series of S\&P500 index returns and a number of parametric models suggested in the literature as well and flexible semiparametric models, we investigate the shape of DNIC, as well as forecasting abilities of these models. The semiparametric approach reveals that the DNIC has complicated shapes characterized by non‐symmetry with respect to past returns and their signs, heterogeneity across the thresholds, and changes over time. Simple parametric models often miss some important features of the DNIC, but some nevertheless exhibit superior out‐of‐sample performance.
I analyze damage from hurricane strikes on the United States since 1955. Using machine learning methods to select the most important drivers for damage, I show that large errors in a hurricane’s predicted landfall location result in higher damage. This relationship holds across a wide range of model specifications and when controlling for ex-ante uncertainty and potential endogeneity. Using a counterfactual exercise I find that the cumulative reduction in damage from forecast improvements since 1970 is about $82 billion, which exceeds the U.S. government’s spending on the forecasts and private willingness to pay for them.
This paper proposes a new family of multifrequency-band tests for the white noise hypothesis by using the maximum overlap discrete wavelet packet transform. At each scale, the proposed multifrequency-band test has the chi-square asymptotic null distribution under mild conditions, which allow the data to be heteroskedastic. Moreover, an automatic multifrequency-band test is further proposed by using a data-driven method to select the scale, and its asymptotic null distribution is chi-square with one degree of freedom. Both multifrequency-band and automatic multifrequency-band tests are shown to have the desirable size and power performance by simulation studies, and their usefulness is further illustrated by two applications. As an extension, similar tests are given to check the adequacy of linear time series regression models, based on the unobserved model residuals.
This research starts from the observation that common desmoothing models are likely to generate some extreme returns that will distort risk measurement and hence can lead to investment decisions that are suboptimal relative to those that would be made if a transaction‐based index were available. Thus, we propose to improve the desmoothing models by incorporating a robust filter into the procedure. We report that in addition to properly treating for smoothing, the method prevents the occurrence of extreme values. As shown with U.S. data, our method leads to desmoothed series whose characteristics are akin to those of transaction‐based indices.
This article is protected by copyright. All rights reserved
Credit default swaps (CDS) have been used to speculate on the default risk of the reference entity. The risk of CDS can be measured by their second moments. We apply a Glosten, Jagannathan, and Runkle (GJR)‐t model for the conditional variance and a Dynamic Conditional Correlation (DCC)‐t model for the conditional correlation. Based on the CDS of six large US banks from 2002 to 2018, we find that CDS conditional variance is asymmetric and leptokurtic. A positive innovation actually increases CDS conditional variance more than a negative innovation does. CDS conditional correlations have stayed elevated since the financial crisis, in contrast to the decreasing stock conditional correlations.
In this paper, I propose a natural extension of time-invariant coefficients threshold GARCH (TGARCH) processes to time-varying one, in which the associated volatility switch between different regimes due to dependency of its coefficients on unobservable (latent) time homogeneous Markov chain with finite state space (MS-TGARCH). These models are showed to be capable to capture some phenomena observed for most financial time series, among others, the asymmetric patterns, leverage effects, dependency without correlation and tail heaviness. So, some theoretical probabilistic properties of such models are discussed, in particular, we establish firstly necessary and sufficient conditions ensuring the strict stationarity and ergodicity for solution process of MS-TGARCH. Secondary, we extend the standard results for the limit theory of the popular quasi-maximum likelihood estimator (QMLE) for estimating the unknown parameters involved in model and we examine thus the strong consistency of such estimates. The finite-sample properties of QMLE are illustrated by a Monte Carlo study. Our proposed model is applied to model the exchange rates of the Algerian Dinar against the single European currency (Euro).
Purpose
The purpose of this paper is to investigate the risk and economic policy uncertainty (EPU) shocks on China’s equity markets while controlling for changes in sentiments and liquidity.
Design/methodology/approach
The GED-TARCH(1,1)-M procedure is used in estimations to deal with the heteroscedasticity problem.
Findings
Evidence shows that stock returns are positively correlated with predictable volatility and lagged downside risk. This study indicates that the stock returns are negatively correlated with both local and global uncertainty innovations. The test results are robust across different measures of stock returns and model specifications. The global EPU innovations have more profound impact on stock returns than that of Chinese EPU.
Research limitations/implications
The findings are based on the data in the China’s stock market, other global markets may be considered in the future research.
Practical implications
Evidence indicates that a rise in EPU produces a negative effect on stock returns at the time news hits a market; however, investors will be rewarded by a premium as prices rebound in the subsequent period for compensating the investment decision made at a high uncertainty period.
Originality/value
The excess stock returns are negatively related to the EPU innovations, regardless of whether EPU originates from a domestic source or external sources.
Models for conditional heteroskedasticity belonging to the GARCH class are now common tools in many economics and finance applications. Among the many possible competing univariate GARCH models, one of the most interesting groups allows for the presence of the so-called asymmetry or leverage effect. In our view, asymmetry and leverage are two distinct phenomena, both inspired by the seminal work of Black in 1976. We propose definitions of leverage and asymmetry that build on the News Impact Curve, allowing to easily and coherently verify if they are both present. We show that several GARCH models are asymmetric but none is allowing for a proper leverage effect. Finally, we extend the leverage definition to a local leverage effect and show that the AGARCH model is coherent with the presence of local leverage. An empirical analysis completes the paper.
This paper examines the efficient market hypothesis by applying monthly data for 15 international equity markets. With the exceptions of Canada and the U.S., the null for the absence of autocorrelations of stock returns is rejected for 13 out of 15 markets. The evidence also rejects the independence of market volatility correlations. The null for testing the absence of correlations between stock returns and lagged news measured by lagged economic policy uncertainty (EPU) is rejected for all markets under investigation. The evidence indicates that a change of lagged EPUs positively predicts conditional variance.
ResearchGate has not been able to resolve any references for this publication.