Structural change and long-range dependence in volatility of exchange rates: either, neither or both?

In this paper, we test for the existence of long memory and structural breaks in the realized variance process for the DM/US$ and Yen/US$ exchange rates. While long memory is evident in the actual processes, a structural break analysis reveals that this feature is partially explained by unaccounted changes in regime. We then compare the forecasting performance of Markov switching models with that of an ARFIMA model. The results indicate that neglecting the break process is not important for very short term forecasting once it is allowed for a long memory component in the model, but that superior forecasts can be obtained at longer horizons by modelling both long memory and structural change.     

High-dimensional covariance forecasting for short intra-day horizons

Asset return covariances at intra-day horizons are known to tend towards zero due to market microstructure effects. Thus, traders who simply scale their daily covariance forecast to match their trading horizon are likely to over-estimate the actual experienced asset dependence. In this paper, some of the key challenges are discussed that are encountered when forecasting high-dimensional covariance matrices for short intra-day horizons. Based on a novel evaluation methodology, and extensive empirical analysis, specific recommendations are made regarding model design and data sampling.     

Conditional volatility persistence and volatility spillovers in the foreign exchange market

I investigate the magnitudes and determinants of volatility spillovers in the foreign exchange (FX) market, using realized measures of volatility and heterogeneous autoregressive (HAR) models. I confirm both meteor shower effects (i.e., inter-regional volatility spillovers) and heat wave effects (i.e., intra-regional volatility spillovers) in the FX market. Furthermore, I find that conditional volatility persistence is the dominant channel linking the changing market states of each region to future volatility and its spillovers. Market state variables contribute to more than half of the explanatory power in predicting conditional volatility persistence, with the model that calibrates volatility persistence and spillovers conditionally on market states performing statistically and economically better. The utilization of market state variables significantly extends our understanding of the economic mechanisms of volatility persistence and spillovers and sheds new light on econometric techniques for volatility modeling and forecasting.     

Combining long memory and level shifts in modelling and forecasting the volatility of asset returns

We propose a parametric state space model of asset return volatility with an accompanying estimation and forecasting framework that allows for ARFIMA dynamics, random level shifts and measurement errors. The Kalman filter is used to construct the state-augmented likelihood function and subsequently to generate forecasts, which are mean and path-corrected. We apply our model to eight daily volatility series constructed from both high-frequency and daily returns. Full sample parameter estimates reveal that random level shifts are present in all series. Genuine long memory is present in most high-frequency measures of volatility, whereas there is little remaining dynamics in the volatility measures constructed using daily returns. From extensive forecast evaluations, we find that our ARFIMA model with random level shifts consistently belongs to the 10% Model Confidence Set across a variety of forecast horizons, asset classes and volatility measures. The gains in forecast accuracy can be very pronounced, especially at longer horizons.     

Financial turbulence,systemic risk and the predictability of stock market volatility

This paper adds a novel perspective to the literature by exploring the predictive performance of two relatively unexplored indicators of financial conditions, i.e. financial turbulence and systemic risk, over stock market volatility using a sample of seven emerging and advanced economies. The two financial indicators that we utilize in our predictive setting provide a unique perspective on market conditions, as they relate directly to portfolio performance metrics from both volatility and co-movement perspectives and, unlike other macro-financial indicators of uncertainty, or risk, can be integrated into diversification models within forecasting and portfolio design settings. Since the data for the two predictors are available at a weekly frequency, and our focus is to produce forecasts at the daily frequency, we use the generalized autoregressive conditional heteroskedasticity-mixed data sampling (GARCH-MIDAS) approach. The results suggest that incorporating the two financial indicators (singly and jointly) indeed improves the out-of-sample predictive performance of stock market volatility models over both the short and long horizons. We observe that the financial turbulence indicator that captures asset price deviations from historical patterns does a better job when it comes to the out-of-sample prediction of future returns compared with the measure of systemic risk, captured by the absorption ratio. The outperformance of the financial turbulence indicator implies that unusual deviations in not only asset returns, but also in correlation patterns play a role in the persistence of return volatility. Overall, the findings provide an interesting opening for portfolio design purposes, in that financial indicators, which are directly associated with portfolio diversification performance metrics, can also be utilized for forecasting purposes, with significant implications for dynamic portfolio allocation strategies.     

Another look at the forecast performance of ARFIMA models

This paper investigates the out-of-sample forecast performance of the autoregressive fractionally integrated moving average [ARFIMA (0,d,0)] specification, both when the underlying value of the fractional differencing parameter (d) is known a priori and when it is unknown. Forecast performance is measured relative to simple deterministic models and a random walk model, for forecast horizons up to 100 periods ahead. Overall, the linear models tend to outperform the ARFIMA specification for both the positive and negative values of d for the simulated series, and for positive d values from the real time-series data. The results of the study question the use of the ARFIMA specification as a forecast tool.     

Volatility forecasting in the Chinese commodity futures market with intraday data

Given the unique institutional regulations in the Chinese commodity futures market as well as the characteristics of the data it generates, we utilize contracts with three months to delivery, the most liquid contract series, to systematically explore volatility forecasting for aluminum, copper, fuel oil, and sugar at the daily and three intraday sampling frequencies. We adopt popular volatility models in the literature and assess the forecasts obtained via these models against alternative proxies for the true volatility. Our results suggest that the long memory property is an essential feature in the commodity futures volatility dynamics and that the ARFIMA model consistently produces the best forecasts or forecasts not inferior to the best in statistical terms.     

Volatility forecasting of crude oil futures market: Which structural change-based HAR models have better performance?

The paper focuses on the smooth and sharp structural changes in crude oil futures volatility and singles out the flexible Fourier form (FFF) and the modified ICSS algorithm to detect them, respectively, so as to explore whether different structural change-based HAR models exhibit significantly better performance for crude oil return volatility forecasting than traditional HAR-type models. The empirical results indicate that, on the one hand, crude oil market displays a strong evidence of breaks, and the incorporation of trigonometric terms can account for the structural changes in crude oil return volatility. On the other hand, the flexible Fourier form (FFF) based HAR-type models and the Structural Breakpoints (SB) based HAR-type models yield superior forecasting performance than traditional HAR-type models. Meanwhile, the forecasting results and economic performance of the former usually outperform the latter, particularly for the short- and medium-term forecasts.     

Capturing volatility persistence: a dynamically complete realized EGARCH-MIDAS model

We introduce extensions of the Realized Exponential GARCH model (REGARCH) that capture the evident high persistence typically observed in measures of financial market volatility in a tractable fashion. The extensions decompose conditional variance into a short-term and a long-term component. The latter utilizes mixed-data sampling or a heterogeneous autoregressive structure, avoiding parameter proliferation otherwise incurred by using the classical ARMA structures embedded in the REGARCH. The proposed models are dynamically complete, facilitating multi-period forecasting. A thorough empirical investigation with an exchange-traded fund that tracks the S&P500 Index and 20 individual stocks shows that our models better capture the dependency structure of volatility. This leads to substantial improvements in empirical fit and predictive ability at both short and long horizons relative to the original REGARCH. A volatility-timing trading strategy shows that capturing volatility persistence yields substantial utility gains for a mean–variance investor at longer investment horizons.     

Dependence and mean reversion in stock prices: The case of the MENA region

This paper provides empirical evidence on the long memory behavior of the stock markets of Egypt, Jordan, Morocco, and Turkey. To test for long memory in the returns and volatility, we employ the modified rescaled range statistic R/S proposed by Lo [Lo, A.W., 1991. Long-term memory in stock market prices. Econometrica 59, 1279–1313] and the recently proposed rescaled variance V/S statistic developed by Giraitis et al. [Giraitis, L., Kokoszka, P.S. Leipus, R., Teyssiere, G., 2003. Rescaled variance and related tests for long memory in volatility and levels. J. Econ. 112, 265–294]. Further analysis is conducted by employing the ARFIMA (p, d, q) model to estimate the long memory parameters. Egypt and Morocco show evidence of long memory in the return series, while Jordan and Turkey display negative persistence. For the volatility series, long memory is conclusively demonstrated for all markets. Then, we compare the forecasting performance of ARMA and ARFIMA models and find that the ARFIMA model outperforms in out-of-sample forecasting of the markets. Our results should be useful to regulators, practitioners and derivative market participants, whose success depends on the ability to forecast stock price movements in these markets.     

Forecasting oil price realized volatility using information channels from other asset classes

Motivated from Ross (1989) who maintains that asset volatilities are synonymous to the information flow, we claim that cross-market volatility transmission effects are synonymous to cross-market information flows or “information channels” from one market to another. Based on this assertion we assess whether cross-market volatility flows contain important information that can improve the accuracy of oil price realized volatility forecasting. We concentrate on realized volatilities derived from the intra-day prices of the Brent crude oil and four different asset classes (Stocks, Forex, Commodities and Macro), which represent the different “information channels” by which oil price volatility is impacted from. We employ a HAR framework and estimate forecasts for 1-day to 66-days ahead. Our findings provide strong evidence that the use of the different “information channels” enhances the predictive accuracy of oil price realized volatility at all forecasting horizons. Numerous forecasting evaluation tests and alternative model specifications confirm the robustness of our results.     

Evaluating the performance of futures hedging using factors-driven realized volatility

The complexity and uncertainty of the financial market mainly stem from the rich market internal transaction information and a wide range effect of external factors. To this end, this paper proposes the combination factors-driven forecasting method to predict realized volatilities of the CSI 300 index and index futures. Based on the volatilities predicted by the proposed method, we further evaluate the ex-ante hedging performance in comparison to the conventional HAR model as well as GARCH-type models. The empirical results indicate that the factors-driven realized volatility model significantly dominates the other commonly used models in terms of hedging effectiveness. Furthermore, the superiority of the proposed method is robust in different market conditions, including significant rising or falling and abnormal market fluctuations in the COVID-19 pandemic, and in different index markets. Therefore, this paper improves the prediction accuracy of volatility by integrating market internal transaction information and external factor information, and the proposed method in this paper can be used by investors to obtain an excellent hedging effect.     

A Comparison of Alternative Forecast Models of REIT Volatility

This study compares the relative performance of several well-known models in the forecasting of REIT volatility. Overall our results suggest that long-memory models (ARFIMA & FIGARCH) provide the best forecasts. Using either a large sample or some statistically justified small subsamples, we find that long memory models consistently outperform their short-memory counterparts (GARCH & Stochastic Volatility models) over a variety of forecast horizons. We also find that asymmetric models (EGARCH & FIEGARCH) are the worst performers among all models. Our study complements and extends a recent study of Cotter and Stevenson (2008) which demonstrates the usefulness of long-memory models in modeling REIT volatility. We conclude that in addition to modeling REIT volatility, long-memory models should also be adopted to forecast REIT volatility.     

Profitability of time series momentum

We propose a continuous-time heterogeneous agent model consisting of fundamental, momentum, and contrarian traders to explain the significant time series momentum. We show that the performance of momentum strategy is determined by both time horizon and the market dominance of momentum traders. Specifically, when momentum traders are more active in the market, momentum strategies with short (long) time horizons stabilize (destabilize) the market, and meanwhile the market under-reacts (over-reacts) in short-run (long-run). This provides profit opportunity for time series momentum strategies with short horizons and reversal with long horizons. When momentum traders are less active in the market, they always lose. The results provide an insight into the profitability of time series momentum documented in recent empirical studies.     

Forecasting hedge fund volatility: a Markov regime-switching approach

The article addresses forecasting volatility of hedge fund (HF) returns by using a non-linear Markov-Switching GARCH (MS-GARCH) framework. The in- and out-of-sample, multi-step ahead volatility forecasting performance of GARCH(1,1) and MS-GARCH(1,1) models is compared when applied to 12 global HF indices over the period of January 1990 to October 2010. The results identify different regimes with periods of high and low volatility for most HF indices. In-sample estimation results reveal a superior performance of the MS-GARCH model. The findings show that regime switching is related to structural changes in the market factor for most strategies. Out-of-sample forecasting shows that the MS-GARCH formulation provides more accurate volatility forecasts for most forecast horizons and for most HF strategies. Inclusion of MS dynamics in the GARCH specification highly improves the volatility forecasts for those strategies that are particularly sensitive to general macroeconomic conditions, such as Distressed Restructuring and Merger Arbitrage.     

Forecasting volatility of crude oil futures using a GARCH–RNN hybrid approach

Volatility is an important element for various financial instruments owing to its ability to measure the risk and reward value of a given financial asset. Owing to its importance, forecasting volatility has become a critical task in financial forecasting. In this paper, we propose a suite of hybrid models for forecasting volatility of crude oil under different forecasting horizons. Specifically, we combine the parameters of generalized autoregressive conditional heteroscedasticity (GARCH) and Glosten–Jagannathan–Runkle (GJR)-GARCH with long short-term memory (LSTM) to create three new forecasting models named GARCH–LSTM, GJR-LSTM, and GARCH-GJRGARCH LSTM in order to forecast crude oil volatility of West Texas Intermediate on different forecasting horizons and compare their performance with the classical volatility forecasting models. Specifically, we compare the performances against existing methodologies of forecasting volatility such as GARCH and found that the proposed hybrid models improve upon the forecasting accuracy of Crude Oil: West Texas Intermediate under various forecasting horizons and perform better than GARCH and GJR-GARCH, with GG–LSTM performing the best of the three proposed models at 7-, 14-, and 21-day-ahead forecasts in terms of heteroscedasticity-adjusted mean square error and heteroscedasticity-adjusted mean absolute error, with significance testing conducted through the model confidence set showing that GG–LSTM is a strong contender for forecasting crude oil volatility under different forecasting regimes and rolling-window schemes. The contribution of the paper is that it enhances the forecasting ability of crude oil futures volatility, which is essential for trading, hedging, and purposes of arbitrage, and that the proposed model dwells upon existing literature and enhances the forecasting accuracy of crude oil volatility by fusing a neural network model with multiple econometric models.     

Harnessing jump component for crude oil volatility forecasting in the presence of extreme shocks

Oil markets are subject to extreme shocks (e.g. Iraq’s invasion of Kuwait), causing the oil market price exhibits extreme movements, called jumps (or spikes). These jumps pose challenges on oil market volatility forecasting using conventional volatility dynamic models (e.g. GARCH model) This paper characterizes dynamics of jumps in oil market price using high frequency data from three perspectives: the probability (or intensity) of jump occurrence, the sign (e.g. positive or negative) of jumps, and the concurrence with stock market jumps. And then, the paper exploits predictive ability of these jump-related information for oil market volatility forecasting under the mixed data sampling (MIDAS) modeling framework. Our empirical results show that augmenting standard MIDAS model using the three jump-related information significantly improves the accuracy of oil market volatility forecasting. The jump intensity and negative jump size are particularly useful for predicting future oil volatility. These results are widely consistent across a variety of robustness tests. This work provides new insights on how to forecast oil market volatility in the presence of extreme shocks.     

Forecasting Value-at-Risk using high frequency data: The realized range model

Current studies on financial market risk measures usually use daily returns based on GARCH type models. This paper models realized range using intraday high frequency data based on CARR framework and apply it to VaR forecasting. Kupiec LR test and dynamic quantile test are used to compare the performance of VaR forecasting of realized range model with another intraday realized volatility model and daily GARCH type models. Empirical results of Chinese Stock Indices show that realized range model performs the same with realized volatility model, which performs much better than daily models.     

我国基金选股选时能力实证分析

本文运用西方基金绩效评价中较为常见的选股选时能力模型及其FF3改进模型对我国证券投资基金进行实证研究,在处理过程中考虑了不同取样频率和不同样本区间的影响.研究结果表明:(1)我国基金只存在很小程度的选股能力,而基本不存在选时能力,更没有基金同时具有选时能力和选股能力;(2)多因素改进模型与原模型相比显著提高了解释能力,说明在可能的情况下应尽可能使用多因素模型;(3)加快取样频率后基金表现出更强一些的选股能力,但在各年度内基金的选股能力有所差异.     

Forecasting value-at-risk and expected shortfall using fractionally integrated models of conditional volatility: International evidence

The present study compares the performance of the long memory FIGARCH model, with that of the short memory GARCH specification, in the forecasting of multi-period value-at-risk (VaR) and expected shortfall (ES) across 20 stock indices worldwide. The dataset is composed of daily data covering the period from 1989 to 2009. The research addresses the question of whether or not accounting for long memory in the conditional variance specification improves the accuracy of the VaR and ES forecasts produced, particularly for longer time horizons. Accounting for fractional integration in the conditional variance model does not appear to improve the accuracy of the VaR forecasts for the 1-day-ahead, 10-day-ahead and 20-day-ahead forecasting horizons relative to the short memory GARCH specification. Additionally, the results suggest that underestimation of the true VaR figure becomes less prevalent as the forecasting horizon increases. Furthermore, the GARCH model has a lower quadratic loss between actual returns and ES forecasts, for the majority of the indices considered for the 10-day and 20-day forecasting horizons. Therefore, a long memory volatility model compared to a short memory GARCH model does not appear to improve the VaR and ES forecasting accuracy, even for longer forecasting horizons. Finally, the rolling-sampled estimated FIGARCH parameters change less smoothly over time compared to the GARCH models. Hence, the parameters' time-variant characteristic cannot be entirely due to the news information arrival process of the market; a portion must be due to the FIGARCH modelling process itself.