Volatility forecasting in European government bond markets

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.     

Exchange rates and oil prices: A multivariate stochastic volatility analysis

This paper uses the multivariate stochastic volatility (MSV) and the multivariate GARCH (MGARCH) models to investigate the volatility interactions between the oil market and the foreign exchange (FX) market, in an attempt to extract information intertwined in the two for better volatility forecast. Our analysis takes into account structural breaks in the data. We find that when the markets are relatively calm (before the 2008 crisis), both oil and FX markets respond to shocks simultaneously and therefore no interaction is detected in daily data. However, during turbulent time, there is bi-directional volatility interaction between the two. In other words, innovations that hit one market also have some impact on the other at a later date and thus using such a dependence significantly improves the forecasting power of volatility models. The MSV models outperform others in fitting the data and forecasting exchange rate volatility. However, the MGARCH models do better job in forecasting oil volatility.     

Adding dummy variables: A simple approach for improved volatility forecasting in electricity market

This study used dummy variables to measure the influence of day-of-the-week effects and structural breaks on volatility. Considering day-of-the-week effects, structural breaks, or both, we propose three classes of HAR models to forecast electricity volatility based on existing HAR models. The estimation results of the models showed that day-of-the-week effects only improve the fitting ability of HAR models for electricity volatility forecasting at the daily horizon, whereas structural breaks can improve the in-sample performance of HAR models when forecasting electricity volatility at daily, weekly, and monthly horizons. The out-of-sample analysis indicated that both day-of-the-week effects and structural breaks contain additional ex ante information for predicting electricity volatility, and in most cases, dummy variables used to measure structural breaks contain more out-of-sample predictive information than those used to measure day-of-the-week effects. The out-of-sample results were robust across three different methods. More importantly, we argue that adding dummy variables to measure day-of-the-week effects and structural breaks can improve the performance of most other existing HAR models for volatility forecasting in the electricity market.     

Forecasting stock price volatility: New evidence from the GARCH-MIDAS model

This paper introduces a combination of asymmetry and extreme volatility effects in order to build superior extensions of the GARCH-MIDAS model for modeling and forecasting the stock volatility. Our in-sample results clearly verify that extreme shocks have a significant impact on the stock volatility and that the volatility can be influenced more by the asymmetry effect than by the extreme volatility effect in both the long and short term. Out-of-sample results with several robustness checks demonstrate that our proposed models can achieve better performances in forecasting the volatility. Furthermore, the improvement in predictive ability is attributed more strongly to the introduction of asymmetry and extreme volatility effects for the short-term volatility component.     

Holidays,weekends and range-based volatility

This study analyses the effect of non-trading periods on the forecasting ability of S&P500 index range-based volatility models. We find that volatility significantly diminishes on the first trading day after holidays and weekends, but not after long weekends. Our findings indicate that models that include autoregressive terms that interact with dummies that allow us to capture changes in volatility levels after interrupting periods provide greater explanatory power than simple autoregressive models. Therefore, the shorter the length of the non-trading periods between two trading days, the higher the overestimation of the volatility if this effect is not considered in volatility forecasting.     

Macroeconomic Forecasting Performance under Alternative Specifications of Time‐Varying Volatility

This paper compares alternative models of time‐varying volatility on the basis of the accuracy of real‐time point and density forecasts of key macroeconomic time series for the USA. We consider Bayesian autoregressive and vector autoregressive models that incorporate some form of time‐varying volatility, precisely random walk stochastic volatility, stochastic volatility following a stationary AR process, stochastic volatility coupled with fat tails, GARCH and mixture of innovation models. The results show that the AR and VAR specifications with conventional stochastic volatility dominate other volatility specifications, in terms of point forecasting to some degree and density forecasting to a greater degree. Copyright © 2014 John Wiley & Sons, Ltd.     

Forecasting the Chinese stock market volatility with international market volatilities: The role of regime switching

The purpose of this paper is to investigate the role of regime switching in the prediction of the Chinese stock market volatility with international market volatilities. Our work is based on the heterogeneous autoregressive (HAR) model and we further extend this simple benchmark model by incorporating an individual volatility measure from 27 international stock markets. The in-sample estimation results show that the transition probabilities are significant and the high volatility regime exhibits substantially higher volatility level than the low volatility regime. The out-of-sample forecasting results based on the Diebold-Mariano (DM) test suggest that the regime switching models consistently outperform their original counterparts with respect to not only the HAR and its extended models but also the five used combination approaches. In addition to point accuracy, the regime switching models also exhibit substantially higher directional accuracy. Furthermore, compared to time-varying parameter, Markov regime switching is found to be a more efficient way to process the volatility information in the changing world. Our results are also robust to alternative evaluation methods, various loss functions, alternative volatility estimators, various sample periods, and various settings of Markov regime switching. Finally, we provide an extension of forecasting aggregate market volatility on monthly frequency and observe mixed results.     

Open interest,volume, and volatility: evidence from Taiwan futures markets

This paper examines the relationships amongst volatility, total trading volume (TVOL) and total open interest (TOI) for three Taiwan stock index futures markets as well as the role of the latter two variables in the dynamics of GARCH modeling and forecasting. From both ex-post and ex-ante perspectives, we study this issue by using the VAR model and augmented GARCH-type models, respectively. For the GARCH-type models, we employ both symmetric and asymmetric models augmented with lagged logs in TOI and/or TVOL. We find that whether addition of these two variables helps the basic GARCH models predict future volatility depends upon the sample period examined for all three sets of futures. Nonetheless, the best three models for out-of-sample volatility forecasting in the MSE sense are generally the augmented models for all sub-intervals and all three futures contracts.     

Forecast on silver futures linked with structural breaks and day-of-the-week effect

Silver future is crucial to global financial markets. However, the existing literature rarely considers the impacts of structural breaks and day-of-the-week effect simultaneously on the volatility of silver future price. Based on heterogeneous autoregressive (HAR) theory, we establish six new type heterogeneous autoregressive (HAR) models by incorporating structural breaks and day-of-the-week effect to forecast the volatility. The empirical results indicate that new models’ accuracy is better than the original HAR model. We find that structural breaks and the day-of-the-week effect contain much forecasting information on silver forecasting. In addition, structural breaks have a positive effect on the silver futures’ volatility. Day-of-the-week effect has a significantly negative influence on silver futures’ price volatility, especially in the mid-term and the long-term. Our works is the first to combine the structural breaks and day-of-the-week effect to identify more market information. This paper provides a better forecasting method to predict silver future volatility.     

Stock market volatility forecasting: Do we need high-frequency data?

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.     

Forecasting the realized volatility of Energy Stock Market: A multimodel comparison

The realized volatility forecasting of energy sector stocks facilitates the establishment of corresponding risk warning mechanisms and investor decisions. In this paper, we collected two different energy sector indices and used different methods, namely principal component analysis (PCA) and sparse principal component analysis (SPCA), to extract features, and combined LSTM and GRU to construct 12 different models. The results show that the SPCA-LSTM model we constructed has the best forecasting performance in the realized volatility forecasting of energy indices, and SPCA has better forecasting results than PCA in the feature extraction stage. The results of the robustness test indicate that our results are robust.     

Are low-frequency data really uninformative? A forecasting combination perspective

In this study, we investigate whether low-frequency data improve volatility forecasting when high-frequency data are available. To answer this question, we utilize four forecast combination strategies that combine low-frequency and high-frequency volatility models and employ a rolling window and a range of loss functions in the framework of the novel Model Confidence Set test. Out-of-sample results show that combination forecasts with GARCH-class models can achieve high forecast accuracy. However, the combination forecast methods appear not to significantly outperform individual high-frequency volatility models. Furthermore, we find that models that combine low-frequency and high-frequency volatility yield significantly better performance than other models and combination forecast strategies in both a statistical and economic sense.     

Volatility forecasting in the Bitcoin market: A new proposed measure based on the VS-ACARR approach

This paper proposes a new volatility-spillover-asymmetric conditional autoregressive range (VS-ACARR) approach that takes into account the intraday information, the volatility spillover from crude oil as well as the volatility asymmetry (leverage effect) to model/forecast Bitcoin volatility (price range). An empirical application to Bitcoin and crude oil (WTI) price ranges shows the existence of strong volatility spillover from crude oil to the Bitcoin market and a weak leverage effect in the Bitcoin market. The VS-ACARR model yields higher forecasting accuracy than the GARCH, CARR, and VS-CARR models regarding out-of-sample forecast performance, suggesting that accounting for the volatility spillover and asymmetry can significantly improve the forecasting accuracy of Bitcoin volatility. The superior forecast performance of the VS-ACARR model is robust to alternative out-of-sample forecast windows. Our findings highlight the importance of accommodating intraday information, spillover from crude oil, and volatility asymmetry in forecasting Bitcoin volatility.     

How does inter-industry spillover improve the performance of volatility forecasting?

This study aims to investigate whether introducing inter-industry spillover information into the GARCH-MIDAS model improves out-of-sample forecasting attempts. We explore the transmission of volatility across sectors, as well as the reliance on inter-industry business links. Our findings demonstrate strong cross-industry volatility spillovers that are related to the degree of the industry-to-industry trading linkage. We compare the out-of-sample volatility forecasting performance of the spillovers-information-incorporated GARCH-MIDAS model with that of the traditional GARCH model. The empirical results show that the GARCH-MIDAS model outperforms traditional GARCH models. Notably, we discover that good (bad) news is always transferred from the back end of the production process to the front end, meaning that economic growth (decline) is driven by consumption expansion (shrinkage).     

Forecasting crude oil price volatility

We use high-frequency intra-day realized volatility data to evaluate the relative forecasting performances of various models that are used commonly for forecasting the volatility of crude oil daily spot returns at multiple horizons. These models include the RiskMetrics, GARCH, asymmetric GARCH, fractional integrated GARCH and Markov switching GARCH models. We begin by implementing Carrasco, Hu, and Ploberger’s (2014) test for regime switching in the mean and variance of the GARCH(1, 1), and find overwhelming support for regime switching. We then perform a comprehensive out-of-sample forecasting performance evaluation using a battery of tests. We find that, under the MSE and QLIKE loss functions: (i) models with a Student’s t innovation are favored over those with a normal innovation; (ii) RiskMetrics and GARCH(1, 1) have good predictive accuracies at short forecast horizons, whereas EGARCH(1, 1) yields the most accurate forecasts at medium horizons; and (iii) the Markov switching GARCH shows a superior predictive accuracy at long horizons. These results are established by computing the equal predictive ability test of Diebold and Mariano (1995) and West (1996) and the model confidence set of Hansen, Lunde, and Nason (2011) over the entire evaluation sample. In addition, a comparison of the MSPE ratios computed using a rolling window suggests that the Markov switching GARCH model is better at predicting the volatility during periods of turmoil.     

Forecasting Bitcoin risk measures: A robust approach

Over the last few years, Bitcoin and other cryptocurrencies have attracted the interest of many investors, practitioners and researchers. However, little attention has been paid to the predictability of their risk measures. This paper compares the predictability of the one-step-ahead volatility and Value-at-Risk of Bitcoin using several volatility models. We also include procedures that take into account the presence of outliers and estimate the volatility and Value-at-Risk in a robust fashion. Our results show that robust procedures outperform non-robust ones when forecasting the volatility and estimating the Value-at-Risk. These results suggest that the presence of outliers plays an important role in the modelling and forecasting of Bitcoin risk measures.     

Forecasting volatility with component conditional autoregressive range model

In this paper, we propose a component conditional autoregressive range (CCARR) model for forecasting volatility. The proposed CCARR model assumes that the price range comprises both a long-run (trend) component and a short-run (transitory) component, which has the capacity to capture the long memory property of volatility. The model is intuitive and convenient to implement by using the maximum likelihood estimation method. Empirical analysis using six stock market indices highlights the value of incorporating a second component into range (volatility) modelling and forecasting. In particular, we find that the proposed CCARR model fits the data better than the CARR model, and that it generates more accurate out-of-sample volatility forecasts and contains more information content about the true volatility than the popular GARCH, component GARCH and CARR models.     

Forecasting exchange rate volatility using high-frequency data: Is the euro different?

We assess the performances of alternative procedures for forecasting the daily volatility of the euro’s bilateral exchange rates using 15 min data. We use realized volatility and traditional time series volatility models. Our results indicate that using high-frequency data and considering their long memory dimension enhances the performance of volatility forecasts significantly. We find that the intraday FIGARCH model and the ARFIMA model outperform other traditional models for all exchange rate series.     

Dynamics of financial returns densities: A functional approach applied to the Bovespa intraday index

We model the stochastic evolution of the probability density functions (PDFs) of Ibovespa intraday returns over business days, in a functional time series framework. We find evidence that the dynamic structure of the PDFs reduces to a vector process lying in a two-dimensional space. Our main contributions are as follows. First, we provide further insights into the finite-dimensional decomposition of the curve process: it is shown that its evolution can be interpreted as a dynamic dispersion-symmetry shift. Second, we provide an application to realized volatility forecasting, with a forecasting ability that is comparable to those of HAR realized volatility models in the model confidence set framework.