Search

This paper proposes to model and forecast realized volatility (RV) using the fractional Ornstein–Uhlenbeck (fO–U) process with a general Hurst parameter, H . A two-stage method is introduced for estimating parameters in the fO–U process based on discrete-sampled observations. In the first stage, H is estimated based on the ratio of two second-order differences of observations from different frequencies. In the second stage, with the estimated H , the other parameters of the model are estimated by the method of moments. All estimators have closed-form expressions and are easy to implement. A large sample theory of the proposed estimators is derived. Extensive simulations show that the proposed estimators and the large-sample theory perform well in finite samples. We apply the model and the method to the logarithmic daily RV series of various financial assets. Our empirical findings suggest that H is much smaller than 1 / 2 , indicating that the RV series have rough sample paths, and that the mean reversion parameter takes a small positive number, indicating that the RV series are stationary but have slow mean reversion. The proposed model is compared with many alternative models, including the fractional Brownian motion, ARFIMA, and HAR, in forecasting RV and logarithmic RV.

This paper develops parameter instability and structural change tests within predictive regressions for economic systems governed by persistent vector autoregressive dynamics. Specifically, in a setting where all – or a subset – of the variables may be fractionally integrated and the predictive relation may feature cointegration, we provide sup-Wald break tests that are constructed using the Local speCtruM (LCM) approach. The new tests cover both parameter variation and multiple structural changes with unknown break dates, and the number of breaks being known or unknown. We establish asymptotic limit theory for the tests, showing that it coincides with standard testing procedures. As a consequence, existing critical values for tied-down Bessel processes may be applied, without modification. We implement the new structural change tests to explore the stability of the fractionally cointegrating relation between implied- and realized volatility (IV and RV). Moreover, we assess the relative efficiency of IV forecasts against a challenging time-series benchmark constructed from high-frequency data. Unlike existing studies, we find evidence that the IV–RV cointegrating relation is unstable, and that carefully constructed time-series forecasts are more efficient than IV in capturing low-frequency movements in RV.

This paper proposes a model for realized variance that exploits information in realized quarticity. The realized variance and quarticity measures are both highly persistent and highly correlated with each other. The proposed model incorporates information from the observed realized quarticity process via autoregressive conditional variance dynamics. It exploits conditional dependence in higher order (fourth) moments in analogy to the class of GARCH models exploit conditional dependence in second moments.

In this paper, we review studies of oil volatility prediction from a new perspective: that of investors who require economic evaluations of forecasting performance. Our results indicate that no single volatility model outperforms all of the competing models, of which GARCH and realized volatility models are the most popular. Most studies evaluate forecasting performance using two criteria: value at risk and hedging effectiveness. Parameter instability and model uncertainty are technical issues that affect out-of-sample performance. Most studies assess volatility forecasts from the perspectives of portfolio management and derivative pricing. Whether oil volatility can predict economic variables and the asset pricing implications of oil volatility for financial markets are important topics that require attention.

Diurnal fluctuations in volatility are a well-documented stylized fact of intraday price data. This warrants an investigation how this intraday periodicity (IP) affects both finite sample as well as asymptotic properties of several popular realized estimators of daily integrated volatility which are based on functionals of a finite number of intraday returns. It turns out that most of the estimators considered in this study exhibit a finite-sample bias due to IP, which can however get negligible when the number of intraday returns diverges to infinity. The appropriate correction factors for this bias are derived based on estimates of the IP. The adequacy of the new corrections is evaluated by means of a Monte Carlo simulation study and an empirical example.

We extend existing studies by considering the higher-order moments relationships among crude oil, gold, and Bitcoin markets. Using high-frequency data from December 2, 2014 to June 10, 2018, we analyze spillovers in jumps and realized second, third, and fourth moments among crude oil, gold, and Bitcoin markets via Granger causality and generalized impulse response analyses. Results suggest evidence of predictability and emphasize, among others, the need of jointly modeling linkages across those three markets with higher-order moments; otherwise, inaccurate risk assessment and investment inferences may arise. The responses of realized volatility shocks are generally positive. Further analyses indicate evidence of a weaker relationship between gold and crude oil and Bitcoin and crude oil compared to the relationship between Bitcoin and gold. Practical implications are also discussed.

We propose the option realized variance as an observable variable to summarize the information from high-frequency option data. This variable aggregates intraday option returns from midquote prices to compute an option’s total variability for a given day, providing additional information about the jump activity in the data generating process. Using the S&P 500 index time series and options data, this paper documents the performance of this realized measure in predicting the index realized variance as well as the equity and variance risk premiums. We estimate an option pricing model and analyze its parameter estimates. Our results show that excluding high-frequency option information produces significant differences in variance jump parameters, estimated risk premiums, and option pricing errors. This paper was accepted by Tyler Shumway, finance.

This paper uses high-frequency stock index data to construct realized volatilities for the Chinese stock market and applies in-sample and out-of-sample to test the predictive power of realized volatility on Chinese stock market returns. The empirical results show that realized volatility can significantly predict the excess return of the Chinese stock market in the next month, and the in-sample and out-of-sample regression models are positive, and the out-of-sample The p-value of the regression model is significant. And after controlling for a range of other stock predictor variables, we find that the regression coefficient of realized volatility is still significant, and we find that after adding realized volatility, the in-sample adj- increases with the inclusion of realized volatility, suggesting that realized volatility does have components that are not explained by other economic variables. Also based on a different construction method, the realized variance still has significant predictive power after averaging the realized variance. After combining two different realized variance indicators, the predictive power is still better. In terms of economic interpretation, this paper finds that the predictive power of realized variance on stock returns is through influencing the turnover rate (market trading activity), which in turn influences stock market returns. We find that realized volatility has a significant effect on the turnover rate, and when we use realized volatility to predict the turnover rate, which in turn predicts the excess return, we find that the coefficient is highly significant, indicating that realized volatility can indeed cause changes in excess return by affecting the turnover rate.

Modern volatility managed indexes employ antiquated close-to-close volatility models to scale exposure. This has material consequences on the option pricing dynamics for structured investments, many of which reference a volatility managed index because of option pricing benefits associated with the constant volatility. The author tests two daily close-to-close models and three intraday “realized volatility” models that leverage the rich information dynamics found in intraday data. The results, across three highly liquid US large-cap indexes, suggest that the latter three models produce more consistent volatility profiles, or alternatively, a lower volatility of volatility, without sacrificing performance (i.e., the Sharpe ratio). All else being equal, this lower volatility of volatility should be preferred by product issuers and investors because of the resulting option pricing benefits.

This study mainly explores whether the implied volatility indices of international stock markets and crude oil contain useful information in predicting the realized volatility (RV) of the German st...

In this paper we examine the predictive power of the heterogeneous autoregressive (HAR) model for the return volatility of major European government bond markets. The results from HAR-type volatility forecasting models show that past short- and medium-term volatility are significant predictors of the term structure of the intraday volatility of European bonds with maturities ranging from 1 year up to 30 years. When we decompose bond market volatility into its continuous and discontinuous (jump) component, we find that the jump component is a significant predictor. Moreover, we show that feedback from past short-term volatility to forecasts of future volatility is stronger in the days that precede monetary policy announcements.

This paper investigates the relation between Treasury futures market volatility and economic policy uncertainty using GARCH-MIDAS. We formulated models with the realized volatility of Treasury futures, the level and volatility of economic policy uncertainty. We find that the realized volatility of Treasury futures and economic policy uncertainty play a significant role in the dynamics of long-run volatility in Treasury futures markets in China and United States.

Forecasting oil price volatility is considered of major importance for numerous stakeholders, including, policy makers, industries and investors. This paper examines and evaluates the main factors that oil price volatility forecasters should take before constructing their forecasting models. Such factors are related to: i) direct vs iterated forecasts, ii) the incorporation of continuous and jump components, iii) the importance of semi variance volatility measures, and iv) OLS vs time-varying parameter (TVP) estimation procedures. Even more, we evaluate the performance of these factors for both realized and implied volatility measures, based on statistical loss functions, as well as, their economic use. The results show that depending on whether end-users are interested in forecasting the realized or the implied volatility, the factors influencing the accuracy of forecasts are different. In particular, for the realized volatility, direct forecasting based on TVP estimation procedure, as well as, using the information obtained in the semi variance measures are capable of producing significantly superior forecasts. By contrast, separating the continuous and the jump components of the realized volatility does not provide any added value to these forecasts. Turning to the OVX, based on the economic evaluation of our forecasts, the TVP estimation procedure seems to performbetter. In addition, we find evidence that the continuous component and the semi variance measures of the realized volatility also yield better OVX forecasts in the longer run horizons.

This research specifically reveals the predictability for the volatility on energy futures markets when involving investor sentiment, using the newly launched China’s INE crude oil futures as an incremental evidence. First, we propose a novel investor sentiment index captures the feature of instant sentiment conversion and the internet attention for energy futures markets. Second, we present the nexus between the proposed novel investor sentiment and conditional volatility, which shows that the proposed investor sentiment significantly impacts on return and volatility. It indicates that the emerging markets filled with noise traders like China are more deeply influenced by investor sentiment and bring about more volatility. Third, the results of dual leverage effects in modeling energy futures volatility shows that the optimistic (pessimistic) sentiment shift has negative(positive) effects on volatility, and downward (upward) shocks from bad news (good news) are followed by greater volatility. Fourth, incorporating the novel investor sentiment into models can significantly improve volatility forecasting accuracy because of its smaller loss function results compared with the benchmark models without sentiment. Moreover, high frequency realized volatility and range-based volatility are regarded as real volatility to examine the predictability, and Diebold Mariano test is used to present the difference of forecasting ability. Our results are robust by using the data from China’s Thermal Coal Futures. Overall, we present that the novel investor sentiment can be utilized for monitoring and predicting volatility shocks for emerging markets with lots of noise traders.

This paper examines the direction and extent of the asymmetric volatility connectedness among international equity markets using 5-minute interval data from 16 stock markets. We analyze asymmetric volatility connectedness using realized volatility and identify the magnitude of the volatility spillover and of the connectedness through networks. We decompose realized volatility into good and bad, and volatility spillover is time-varying and asymmetric. Bad volatility dominates good volatility in international stock markets. Macroeconomic shocks (negative interest rates in Japan, economic stress in China, a recession in Russia, and double-digit inflation in Brazil) increased volatility asymmetry. Asian markets are responsible for stronger negative spillover, thereby necessitating regulations to reduce the strong negative volatility connectedness with Asian markets.

We study the predictive value of transaction activity in the bitcoin network for the realized volatility of bitcoin returns constructed by high-frequency data. As an alternative modeling approach to the popular linear heterogeneous autoregressive model, we provide out-of-sample forecasts for realized volatility of bitcoin returns employing machine learning algorithms, and in particular by Random Forests. Our findings reveal that on-blockchain transaction activity does improve the out-of-sample forecast accuracy at all the forecast horizons considered.

We examine the predictive value of El Niño and La Niña weather episodes for the subsequent realized variance of 16 agricultural commodity prices. To this end, we use high-frequency data covering the period from 2009 to 2020 to estimate the realized variance along realized skewness, realized kurtosis, realized jumps, and realized upside and downside tail risks as control variables. Accounting for the impact of the control variables as well as spillover effects from the realized variances of the other agricultural commodities in our sample, we estimate an extended heterogeneous autoregressive (HAR) model by means of random forests to capture in a purely data-driven way potentially nonlinear links between El Niño and La Niña and the subsequent realized variance. We document such nonlinear links, and that El Niño and La Niña increase forecast accuracy, especially at longer forecast horizons, for several of the agricultural commodities that we study in this research.

This study investigates the effect of financial stress (financial stress index; FSI) on oil market realized volatility using Markov-regime switching MIDAS models. The empirical results show that FS...

Copyright © 2021 The Author(s). The research debate on the informational content embedded in option prices mostly approves the incremental predictive power of implied volatility estimates for financial volatility forecasting beyond that contained in GARCH and realized variance models. Contributing to this ongoing debate, we introduce the novel AIM-HEAVY model, a tetravariate system with asymmetries, option-implied volatility, and economic uncertainty variables beyond daily and intra-daily dispersion measures included in the benchmark HEAVY specification. We associate financial with macroeconomic uncertainties to explore the macro-financial linkages in the high-frequency domain. In this vein, we further focus on economic factors that exacerbate stock market volatility and represent major threats to financial stability. Hence, our findings are directly connected to the current world-wide Coronavirus outbreak. Financial volatilities are already close to their crisis-peaks amid the generalized fear about controversial economic policies to support societies and the financial system, especially in the case of the heavily criticized UK authorities’ delayed and limited response.

We investigate United States Oil Fund volatility predictions using a mixed data sampling modeling framework. There are several vital findings. First, our in-sample analysis shows that both the leverage effect and intraday jumps have a significant impact on the United States Oil Fund realized volatility. Second, our out-of-sample analyses suggest that incorporating the leverage effect can largely improve the United States Oil Fund realized volatility forecasts. Third, using a portfolio exercise, we show that the improved realized volatility forecasts lead to significantly increased economic values. Our results are confirmed by a wide range of robustness checks.

The simplest and most natural vol-of-vol estimator, the pre-estimated spot variance-based realized variance, is typically plagued by a large finite-sample bias. In this paper, we analytically show that allowing for the overlap of consecutive local windows to pre-estimate the spot variance may correct for this bias. In particular, we provide a feasible rule for the bias-optimal selection of the length of local windows when the volatility is a CKLS process. The effectiveness of this rule for practical applications is supported by numerical and empirical analyses.

This paper explores empirically whether the supply or the demand uncertainty, the time to maturity, and the slope of the term structure (storage), explain the realized volatility of nearby commodity futures 5‐min returns. I find support for the “uncertainty resolution” and the “theory of storage” hypotheses while the “time to maturity” hypothesis is rejected. These results are robust to the inclusion of autoregressive terms in the baseline model. Next, I evaluate the in‐ and out‐of‐sample forecasting ability of models including these economic variables and find mixed results. Finally, I test the validity of these forecasts in expected shortfall modeling.

Inclusion of jump component in the price process has been a long debate in finance literature. In this paper, we identify and characterize jump risks in the Canadian stock market using high-frequen...

Ross (2015) shows that options data can reveal the market’s true expectations. Adapting this approach to index options (S&P, FTSE, CAC, SMI and DAX), we separate option-implied volatility into Ross-recovered true expected volatility and a risk preference factor. We investigate whether these factors perform better to forecast realized volatility if constructed locally or globally, yielding new insights to understand international dynamics in risk expectations and preferences. We find evidence of significantly improved realized volatility forecasts. Models using Ross-recovered value-weighted global measures of risk preferences have the best forecasting performances across indices. Risk preferences are best measured globally. Overall, the findings suggest that the Recovery Theorem is useful empirically and accurately recovers the true expected returns distribution and its associated pricing kernel.

Using a machine-learning technique known as random forests, we analyze the role of investor confidence in forecasting monthly aggregate realized stock-market volatility of the United States (US), o...

We analyze the predictive power of time-varying risk aversion for the realized volatility of crude oil returns based on high-frequency data. Using random forests, and their extensions to quantile r...

Recently, to account for low-frequency market dynamics, several volatility models, employing high-frequency financial data, have been developed. However, in financial markets, we often observe that financial volatility processes depend on economic states, so they have a state heterogeneous structure. In this paper, to study state heterogeneous market dynamics based on high-frequency data, we introduce a novel volatility model based on a continuous Ito diffusion process whose intraday instantaneous volatility process evolves depending on the exogenous state variable, as well as its integrated volatility. We call it the state heterogeneous GARCH-Ito (SG-Ito) model. We suggest a quasi-likelihood estimation procedure with the realized volatility proxy and establish its asymptotic behaviors. Moreover, to test the low-frequency state heterogeneity, we develop a Wald test-type hypothesis testing procedure. The results of empirical studies suggest the existence of leverage, investor attention, market illiquidity, stock market comovement, and post-holiday effect in S&P 500 index volatility.

This paper investigates the asymmetric effects of exchange rate volatility in currency markets using high-frequency, intraday data of the most actively traded currencies over 2004–2017. The analysis is conducted by combining the quantile regression model with the heterogeneous autoregressive (HAR) model and its extensions where realized variance is decomposed into positive and negative semivariances. We find that safe haven currencies exhibit behavior different from that of other currencies. For safe haven currencies, negative realized semivariance associated with appreciation plays an important role in explaining the quantile-dependent volatility dynamics. This behavior is more pronounced during high volatility phases. The opposite holds for other currencies, i.e., positive realized semivariance associated with depreciation matters more. The results also reveal that while negative jumps associated with the appreciation of safe haven currencies lead to higher future volatility, positive jumps associated with the depreciation of other currencies lead to higher future volatility, especially during high volatility phases. We formally test whether the volatility dynamics are quantile dependent.

We investigate the second‐moment response to tweets from US President Donald J. Trump in the US stock market. We find that Trump's tweeting positively and significantly affects the volatility and jumps during our sample's later period. The response of realized volatility to tweets is greater than that of continuous volatility because of the jump component in realized volatility. These results suggest that Trump's tweeting affects financial markets by sincreasing the market's jump tail risk, which cannot be hedged by investors without paying extra risk premiums, and therefore it requires careful consideration in investments.

From the autoregressive representation of the portfolio-variance optimization problem, we derive a novel model for conditional portfolio weights as a linear function of past conditional and realized (and, hence, observable) terms. This dynamic conditional weights ( DCW ) approach is benchmarked against popular model-based and model-free specifications in terms of weights forecasts and portfolio allocations. Next to portfolio turnover and variance, we introduce the break-even transaction cost as an additional measure that identifies the range of transaction costs for which one allocation is preferred to another. By comparing minimum-variance portfolios built on the components of the Dow Jones 30 Index, the proposed DCW attains the best allocations overall with respect to the measures considered, for any degree of risk aversion, transaction costs, and exposure.

The general consensus in the volatility forecasting literature is that high-frequency volatility models outperform low-frequency volatility models. However, such a conclusion is reached when low-frequency volatility models are estimated from daily returns. Instead, we study this question considering daily, low-frequency volatility estimators based on open, high, low, and close daily prices. Our data sample consists of 18 stock market indices. We find that high-frequency volatility models tend to outperform low-frequency volatility models only for short-term forecasts. As the forecast horizon increases (up to one month), the difference in forecast accuracy becomes statistically indistinguishable for most market indices. To evaluate the practical implications of our results, we study a simple asset allocation problem. The results reveal that asset allocation based on high-frequency volatility model forecasts does not outperform asset allocation based on low-frequency volatility model forecasts.

Combining forecasts from multiple temporal aggregation levels exploits information differences and mitigates model uncertainty, while reconciliation ensures a unified prediction that supports aligned decisions at different horizons. It can be challenging to estimate the full cross-covariance matrix for a temporal hierarchy, which can easily be of very large dimension, yet it is difficult to know a priori which part of the error structure is most important. To address these issues, we propose to use eigendecomposition for dimensionality reduction when reconciling forecasts to extract as much information as possible from the error structure given the data available. We evaluate the proposed estimator in a simulation study and demonstrate its usefulness through applications to short-term electricity load and financial volatility forecasting. We find that accuracy can be improved uniformly across all aggregation levels, as the estimator achieves state-of-the-art accuracy while being applicable to hierarchies of all sizes.

PurposeThis paper examines the relationship between volatility, sentiment and returns in terms of levels and changes for both lower and higher data frequencies using quantile regression (QR) method.Design/methodology/approachIn the first step, the study applies the Granger causality test to understand the causal relationship between realized volatility, returns and sentiment as levels and changes. In the second step, the study employs a QR method to investigate whether investor sentiment and returns can predict realized volatility. This regression method gives robust results irrespective of distributional assumptions and to outliers in the dependent variable.FindingsEmpirical results show that the VIX volatility index is a better fear gauge of market-wide investors' sentiments and has a predictive power for future realized volatility in terms of levels and changes for both higher and lower data frequencies. This study provides evidence that the relationship between realized volatility, investor sentiment and returns, respectively, is not symmetric for all quantiles of QR, as opposed to OLS regression. Furthermore, this work supports the behavioral theory beyond leverage hypothesis in explaining the asymmetric relation between returns and volatility at higher and lower data frequencies.Originality/valueThis paper adds to the limited understanding of investor sentiment’s impact on volatility by proposing a QR model which provides a more complete picture of the relationship at all parts of the volatility distribution for both higher and lower data frequencies and in terms of levels and changes. To the author knowledge, this is the first paper to study the volatility responses to positive and negative sentiment changes for developed market and to use both lower and higher data frequencies as well as data in terms of levels and changes.

Autoregressive (AR) models such as the heterogeneous autoregressive (HAR) model capture the linear footprint inherent in realized volatility. We draw upon the fact that the HAR model is a constrain...

Se estudió la relación entre los efectos de la pandemia de COVID-19 y la volatilidad realizada. Además, se analizó el posible nexo entre las medidas de mitigación y contención adoptadas por los gobiernos y la volatilidad realizada. El período de estudio abarca del 2 de febrero de 2020 al 28 de agosto del mismo año. Este período a su vez se dividió en catorce muestras dos para cada mes, lo que dio origen a los catorce paneles no balanceados usados en las estimaciones. El método de estimación utilizado es Mínimos Cuadrados Ordinarios con efectos fijos de dos vías y el método de Mínimos Cuadrados Generalizados Estimados (EGLS) con efectos aleatorios de una vía (período). Se utilizaron datos de volatilidad realizada de sesenta y cinco de los principales índices bursátiles. Los resultados exhiben evidencia que apoya la existencia de una relación estadística significativa entre las medidas de contención y mitigación y la volatilidad realizada, principalmente en los meses de febrero y marzo, sin embargo, no se encontró uniformidad en los resultados. Por otro lado, no se encontró evidencia suficiente a favor de la existencia de una relación positiva entre los efectos de la pandemia COVID-19 y la volatilidad realizada.

We propose new break tests for parameters such as mean, variance, quantile and others of panel data sets, in a general setup based on the self-normalization method. The self-normalization tests show much better size than existing tests, resolving their over-size problem for panels with serial dependence, cross-sectional dependence, conditional heteroscedasticity and/or N relative larger than T, which is demonstrated theoretically by a nuisance parameter free limiting null distribution and experimentally by very stable finite sample sizes. The proposed test is also implemented much more easily than the existing tests in that the proposed test needs no bandwidth selection for the long-run variance estimation and is computed very simply. Applications of the self-normalization test to the financial stock return and realized volatility indicate more toward absence of breaks of mean and/or variance than the existing tests which neglect cross-sectional correlation and other features apparent in the data sets.

In this paper, we propose and evaluate a shrinkage based methodology that is designed to improve the accuracy of volatility forecasts. Our approach is based on a two-step procedure for extracting latent common volatility factors from a large dimensional and high-frequency dataset. In the first step, we apply either least absolute shrinkage operator (LASSO) or the elastic net (EN) shrinkage on estimated integrated volatilities, in order to select a subset of assets that are informative about the target asset. In the second step, we utilize (sparse) principal component analysis on the selected assets, in order to estimate latent return factors, which are in turn used to construct latent volatility factors. Our two-step method is found to yield more accurate volatility predictions than a variety of alternative models based on approaches such as direct application of (S)PCA and direct application of LASSO or EN shrinkage, when comparing out-of-sample R 2 s and mean absolute forecasting errors, and when implementing predictive accuracy tests. Additionally model confidence sets are found to contain models solely based on our two-step approach. These forecasting gains are found to be robust to the use of original or log-scale realized volatility models, different data sampling frequencies, and different forecasting sub-periods.

Modeling Bitcoin realized volatility by the heterogeneous autoregressive model is subject to substantial model specification uncertainty in practice. To circumvent the lag specification uncertainty, we introduce a new model averaging coefficient estimator with the mean squared error of the coefficient to be minimized. We show that the averaged coefficient vector has a root- n consistency with n being the sample size and propose using a double bootstrap to provide inference. Monte Carlo simulation results demonstrate reliability of the proposed method. The in-sample application shows that adjustment for measurement errors by HARQ-type models is necessary. The model averaging estimator has higher in-sample explanatory power with more significant predictors. The out-of-sample outcomes reveal that the forecast horizon plays a key role at determining the effectiveness of signed realized variance for predicting the Bitcoin volatility. Finally, the model averaging HARQ-type models demonstrate superior out-of-sample performance for both short and long forecast horizons.

We propose an autoregressive conditional duration (ACD) model with periodic time-varying parameters and multiplicative error form. We name this model periodic autoregressive conditional duration (PACD). First, we study the stability properties and the moment structures of it. Second, we estimate the model parameters, using (profile and two-stage) Gamma quasi-maximum likelihood estimates (QMLEs), the asymptotic properties of which are examined under general regularity conditions. Our estimation method encompasses the exponential QMLE, as a particular case. The proposed methodology is illustrated with simulated data and two empirical applications on forecasting Bitcoin trading volume and realized volatility. We found that the PACD produces better in-sample and out-of-sample forecasts than the standard ACD.

In this paper, we study the cryptocurrency asset pricing via machine learning. The common pricing factors similar to equity asset pricing are constructed. The classical equity-based risk factors including size, momentum, and value to growth from the Fama-French three factor model are studied. For volatility risk factor category, we investigate realized volatility, skewness and jump. We also investigate liquidity factors including bid-ask, volume growth and Roll’s measure. We collect other crypto-unique factors. We show the machine learning models which could handle 30 characteristics together explain most of the excess return of cryptocurrencies.

In this paper, we assess the dynamic impact of the U.S. monetary policy announcements on oil market futures returns and volatility. We use intra-day data for West Texas Intermediate (WTI) oil futures together with a time-varying modeling approach to study the nature of this dynamic impact. In addition, we also control for macroeconomic news shocks and separately study the response of good and bad realized volatility. Evidence suggests that there is a significant time variation in the response of oil returns, as well as its volatility to the Federal Reserve policy announcements. Broadly, we also find that higher (lower) uncertainty about Federal Reserve policy actions is associated with a weaker (stronger) impact of the surprise policy announcements on oil returns and volatility.

Using high frequency data and connectedness measures based on a time-varying parameter vector autoregression (TVP-VAR) model, we study dynamic connectedness among the realized volatility of 15 commodity futures (Gold, Heating oil, Light crude oil, Natural gas, Copper, Platinum, Cocoa, Coffee, Corn, Cotton, Orange Juice, Soybean, Soybean meal, Sugar, and Wheat) from September 22, 2008 to May 28, 2020. The results show strong and moderate levels of volatility connectedness among energy and metals and moderate connectedness levels within the group of agricultural commodities. Cross-commodity connectedness can explain a large portion of volatility connectedness in some cases, highlighting the importance of conducting realized volatility connectedness within a model allowing realized volatilities to be endogenously and simultaneously determined. Connectedness is robust to alternative specifications and varies with time. It is mostly driven by macroeconomic variables and uncertainty, including the term spread of interest rates and real economic activity. However, the analysis shows that some of the drivers of connectedness differ between upper and lower quantiles.

High frequency financial data has become an essential component of the digital economy, yielding an increasing number of estimators. However, it is hard to reliably assess the uncertainty of such estimators. The Observed Asymptotic Variance (observed AVAR) is a non-parametric estimator for (squared) standard error in high frequency data. The device is related to observed information in likelihood theory, but in this case it is non-parametric and uses the high-frequency data structure. An earlier paper has developed the estimator in the case where edge effects are small to moderate. In practical data, it is often more realistic to assume that edge effects can be large, and this is the problem that we tackle in the current paper. We here find a regression approach to observed AVAR which is highly robust to large edges. This approach covers most high frequency estimators.

This paper examines the informational content of Implied Volatility (IV) for 493 Malaysian and 945 Thai structured call warrants from 2014 to 2015. Unlike a regular warrant (issued by the firm) and attached to bonds, loan stocks, or preferred stocks as sweeteners, a structured warrant is issued by a third party. Structured warrant is a prevalent exchange-traded instrument in South-East Asian countries. This study is among the first to examine the IV of structured warrants using emerging market datasets from Bursa Malaysia and the Stock Exchange of Thailand. Our predictive regression models compare IV's effectiveness in anticipating future realized volatility vis-a-vis historical volatility. We record that IV in both exchanges contains relevant information about future realized volatility only on a handful of occasions. Additionally, structured warrants' IV is a mostly biased predictor with a diminutive efficiency threshold. Our findings bear implications for the region's derivatives market growth and risk management practices.

This manuscript extends the literature on the application of geometric Brownian motion. Forecasted drift and diffusion terms estimated separately and recursively are plugged into the framework to forecast S&P500 index values. Expected index values are estimated from 100,000 simulated index values and probabilities. The results of comparing expected index values with actual values indicate that although reliable predictions of S&P500 index values can be obtained at monthly, quarterly, and annual frequencies, the reliability may decrease in that order.