Forecasting volatility: Roles of sampling frequency and forecasting horizon

This study empirically tests how and to what extent the choice of the sampling frequency, the realized volatility (RV) measure, the forecasting horizon and the time‐series model affect the quality of volatility forecasting. Using highly synchronous executable quotes retrieved from an electronic trading platform, the study avoids the influence of various market microstructure factors in measuring RV with high‐frequency intraday data and in inferring implied volatility (IV) from option prices. The study shows that excluding non‐trading‐time volatility produces significant downward bias of RV by as much as 36%. Quality of prediction is significantly affected by the forecasting horizon and RV model, but is largely immune from the choice of sampling frequency. Consistent with prior research, IV outperforms time‐series forecasts; however, the information content of historical volatility critically depends on the choice of RV measure. © 2010 Wiley Periodicals, Inc. Jrl Fut Mark     

A No‐Arbitrage Fractional Cointegration Model for Futures and Spot Daily Ranges

The no‐arbitrage relation between futures and spot prices implies an analogous relation between futures and spot daily ranges. The long‐memory features of the range‐based volatility estimators are analyzed, and fractional cointegration is tested in a semi‐parametric framework. In particular, the no‐arbitrage condition is used to derive a long‐run relationship between volatility measures and to justify the use of a fractional vector error correction model (FVECM) to study their dynamic relationship. The out‐of‐sample forecasting superiority of FVECM, with respect to alternative models, is documented. The results highlight the importance of incorporating the long‐run equilibrium in volatilities to obtain better forecasts, given the information content in the volatility of futures prices. © 2011 Wiley Periodicals, Inc. Jrl Fut Mark 33:77–102, 2013     

Forecasting bitcoin volatility: Evidence from the options market

This paper studies a large number of bitcoin (BTC) options traded on the options exchange Deribit. We use the trades to calculate implied volatility (IV) and analyze if volatility forecasts can be improved using such information. IV is less accurate than AutoRegressive–Moving-Average or Heterogeneous Auto-Regressive model forecasts in predicting short-term BTC volatility (1 day ahead), but superior in predicting long-term volatility (7, 10, 15 days ahead). Furthermore, a combination of IV and model-based forecasts provides the highest accuracy for all forecasting horizons revealing that the BTC options market contains unique information.     

Rational expectations and market efficiency in the U.S. live cattle futures market: The role of proprietary information

The role of proprietary information in forecasting and market efficiency in the U.S. live cattle futures market is investigated. Using a unique proprietary data source collected by a private firm, we test whether the initial estimates in the USDA Cattle on Feed Report and the Knight‐Ridder pre‐release forecasts are unbiased and efficient forecasts of final revised USDA Cattle on Feed Report numbers. We then use these results to test whether futures price movements are predictable based on information in the proprietary data. We also test whether the initial estimates from the Cattle on Feed Report have new information that moves prices once the information contained in the proprietary data source has been taken into account. Results suggest that the information contained in the proprietary data source does have statistically significant explanatory power for forecasting final revised Cattle on Feed Report numbers and for predicting short‐term price movements of futures contracts. The results are inconsistent with strong‐form market efficiency in the live cattle futures market. We also find that the initial estimates in the Cattle on Feed Report still have new information that moves prices even after accounting for the unique information in both the Knight‐Ridder pre‐release forecasts and the proprietary data. © 2004 Wiley Periodicals, Inc. Jrl Fut Mark 24:429–451, 2004     

Do futures prices help forecast the spot price?

This study proposes a futures‐based unobserved components model for commodity spot prices. Prices quoted at the same time incorporate the same information, but are affected differently, resulting in the different shapes of futures curves. This model utilizes information from part of the futures curve to improve forecasting accuracy of the spot price. Applying this model to oil market data, I find that the model forecasts outperform the literature benchmark (the no‐change forecast) and futures prices forecasts in multiple dimensions, with smaller average error variation over the sample period and higher chance of smaller absolute error in each period.     

Forecasting performance of extreme‐value volatility estimators

This study evaluates the forecasting performance of extreme‐value volatility estimators for the equity‐based Nifty Index using two‐scale realized volatility. This benchmark mitigates the effect of microstructure noise in the realized volatility. Extreme‐value estimates with relatively simple forecasting methods provide substantially better short‐term and long‐term forecasts, compared to historical volatility. The higher efficiency of extreme‐value estimators is primarily responsible for this improvement. The extent of possible improvement in forecasts is likely to be economically significant for applications like options pricing. By including extremevalue estimators, the forecasting performance of generalized autoregressive conditional heteroscedasticity (GARCH) can also be improved. © 2007 Wiley Periodicals, Inc. Jrl Fut Mark 27: 1085–1105, 2007     

Does Index Futures Trading Reduce Volatility in the Chinese Stock Market? A Panel Data Evaluation Approach

This study investigates the effect of introducing index futures trading on the spot price volatility in the Chinese stock market. We employ a recently developed panel data policy evaluation approach (Hsiao, Ching, and Wan, 2011) to construct counterfactuals of the spot market volatility, based mainly on cross‐sectional correlations between the Chinese and international stock markets. This new method does not need to specify a particular regression or a time‐series model for the volatility process around the introduction date of index futures trading, and thus avoids the potential omitted variable bias caused by uncontrolled market factors in the existing literature. Our results provide empirical evidence that the introduction of index futures trading significantly reduces the volatility of the Chinese stock market, which is robust to different model selection criteria and various prediction approaches. © 2012 Wiley Periodicals, Inc. Jrl Fut Mark 33:1167–1190, 2013     

Implied volatility forecasts in the grains complex

This article finds that the implied volatilities of corn, soybean, and wheat futures options 4 weeks before option expiration have significant predictive power for the underlying futures contract return volatilities through option expiration from January 1988 through September 1999. These implied volatilities also encompass the information in out‐of‐sample seasonal Glosten, Jagannathan, and Runkle (GJR;1993) volatility forecasts. Evidence also demonstrates that when corn‐implied volatility rises relative to out‐of‐sample seasonal GJR volatility forecasts, implied volatility substantially overpredicts realized volatility. However, simulations of trading rules that involve selling corn option straddles when corn‐implied volatility is high relative to out‐of‐sample GJR volatility forecasts indicate that none of the trading rules would have been significantly profitable. This finding suggests that these options are not necessarily overpriced. © 2002 Wiley Periodicals, Inc. Jrl Fut Mark 22:959–981, 2002     

VIX futures and its closed‐form pricing through an affine GARCH model with realized variance

This paper studies the forecasting of volatility index (VIX) and the pricing of its futures by a generalized affine realized volatility model proposed by Christoffersen et al. This model is a weighted average of a GARCH and a pure realized variance (RV) model that incorporates each volatility component into the new dynamics. We rewrite the VIX in terms of both volatility components and then derive closed‐form formulas for the VIX forecasting and its futures pricing. Our empirical studies find that a unification of the GARCH and the RV in the modeling substantially improves the forecasting of this index and the pricing of its futures.     

Dividend‐Rollover Effect and the Ad Hoc Black‐Scholes Model

One of the most widely used option‐valuation models among practitioners is the ad hoc Black‐Scholes (AHBS) model. The main contribution of this study is methodological. We carefully consider three dividend strategies (No dividend, Implied‐forward dividend, and Actual dividend) for the AHBS model to investigate their effect on pricing errors. We suggest a new dividend strategy, implied‐forward dividend, which incorporates expectational information on dividends embedded in option prices. We demonstrate that our implied‐forward dividend strategy produces more consistent estimates between in‐sample market and model option prices. More importantly our new implied‐forward dividend strategy makes more accurate out‐of‐sample forecasts for one‐day or one‐week ahead prices. Second, we document that both a “Return‐volatility” Smile and a “Return‐pricing Error” Smile exist. From these return characteristics, we make two conclusions: (1) the return dependency of implied volatility is an important explanatory variable and should be controlled to reduce the pricing error of an AHBS model, and (2) it is important for the hedging horizon to be based on return size, that is, the larger the contemporaneous return, the more frequent an option issuer must rebalance the option's hedge. © 2012 Wiley Periodicals, Inc. Jrl Fut Mark 32:742‐772, 2012     

Predicting financial volatility: High‐frequency time‐series forecasts vis‐à‐vis implied volatility

Recent evidence suggests option implied volatilities provide better forecasts of financial volatility than time‐series models based on historical daily returns. In this study both the measurement and the forecasting of financial volatility is improved using high‐frequency data and long memory modeling, the latest proposed method to model volatility. This is the first study to extract results for three separate asset classes, equity, foreign exchange, and commodities. The results for the S&P 500, YEN/USD, and Light, Sweet Crude Oil provide a robust indication that volatility forecasts based on historical intraday returns do provide good volatility forecasts that can compete with and even outperform implied volatility. © 2004 Wiley Periodicals, Inc. Jrl Fut Mark 24:1005–1028, 2004     

Properties and the predictive power of implied volatility in the New Zealand dairy market

This study develops a dairy implied volatility index (DVIX), derived from New Zealand Exchange traded options on whole milk powder (WMP) futures. We document an inverse return–volatility relation which is asymmetric, where increases in WMP futures prices are associated with larger absolute changes in the DVIX than decreases. In sample, the results strongly suggest that the DVIX has a high information content regarding conditional variance and that the inclusion of historical information further improves the predictive power. Out of sample, we find that the DVIX provides substantial information about future realized volatility. We also document that a combination of historical volatility and the DVIX provides the best out-of-sample forecasts.     

Forecasting volatility

The forecasting ability of the most popular volatility forecasting models is examined and an alternative model developed. Existing models are compared in terms of four attributes: (1) the relative weighting of recent versus older observations, (2) the estimation criterion, (3) the trade‐off in terms of out‐of‐sample forecasting error between simple and complex models, and (4) the emphasis placed on large shocks. As in previous studies, we find that financial markets have longer memories than reflected in GARCH(1,1) model estimates, but find this has little impact on outofsample forecasting ability. While more complex models which allow a more flexible weighting pattern than the exponential model forecast better on an in‐sample basis, due to the additional estimation error introduced by additional parameters, they forecast poorly out‐of‐sample. With the exception of GARCH models, we find that models based on absolute return deviations generally forecast volatility better than otherwise equivalent models based on squared return deviations. Among the most popular time series models, we find that GARCH(1,1) generally yields better forecasts than the historical standard deviation and exponentially weighted moving average models, though between GARCH and EGARCH there is no clear favorite. However, in terms of forecast accuracy, all are dominated by a new, simple, nonlinear least squares model, based on historical absolute return deviations, that we develop and test here. © 2005 Wiley Periodicals, Inc. Jrl Fut Mark 25:465–490, 2005     

Investor Sentiment and Return Predictability in Agricultural Futures Markets

This study examines the usefulness of trader‐position‐based sentiment index for forecasting future prices in six major agricultural futures markets. It has been found that large speculator sentiment forecasts price continuations. In contrast, large hedger sentiment predicts price reversals. Small trader sentiment hardly forecasts future market movements. An investigation was performed into various sentiment‐based timing strategies, and it was found that the combination of extreme large trader sentiments provides the strongest timing signal. These results are generally consistent with the hedging‐pressure theory, suggesting that hedgers pay risk premiums to transfer nonmarketable risks in futures markets. Moreover, it does not appear that large speculators in the futures markets possess any superior forecasting ability. © 2001 John Wiley & Sons, Inc. Jrl Fut Mark 21:929–952, 2001     

Role of delivery options in basis convergence

The corn futures contract, traded on the Chicago Board of Trade, provides sellers with delivery options about the timing of delivery, the location of delivery, and the grade to be delivered. These options presumably have values that can vary from one delivery month to the next. The joint values of the timing and location options are estimated for each delivery month for the years 1989 through 1997. These estimates are then used in regression models to determine the degree to which they influence basis variability on the first day of the maturity month. Econometric models are also developed to see if the estimated implicit options values are useful in improving the forecasts of basis convergence over the 2‐month period prior to maturity. The results suggested that variation in the delivery options values in the corn futures contract does indeed help explain basis variability on the first day of maturity. An option‐value variable, based on estimated values two months prior to maturity, resulted in occasional, small improvements (from a statistical point of view) in the precision of forecasts. The existence of delivery options increases basis variability at maturity, but it is difficult to use this information to improve forecasts of basis convergence. One limitation of the analysis is that the Chicago cash market had few transactions per day during the sample period, and hence the reported spot prices may be inadequate for making high‐quality estimates of the options values. © 2002 Wiley Periodicals, Inc. Jrl Fut Mark 22:783–809, 2002     

Modeling discontinuous periodic conditional volatility: Evidence from the commodity futures market

This paper examines a wide variety of models that allow for complex and discontinuous periodic variation in conditional volatility. The value of these models (including augmented versions of existing models) is demonstrated with an application to high frequency commodity futures return data. Their use is necessary, in this context, because commodity futures returns exhibit discontinuous intraday and interday periodicities in conditional volatility. The former of these effects is well documented for various asset returns; however, the latter is unique amongst commodity futures returns, where contract delivery and climate are driving forces. Using six years of high‐frequency cocoa futures data, the results show that these characteristics of conditional return volatility are most adequately captured by a spline‐version of the periodic generalized autoregressive conditional heteroscedastic (PGARCH) model. This model also provides superior forecasts of future return volatility that are robust to variation in the loss function assumed by the user, and are shown to be beneficial to users of Value‐at‐Risk (VaR) models. © 2004 Wiley Periodicals, Inc. Jrl Fut Mark 24:805–834, 2004     

Testing mean reversion in financial market volatility: Evidence from S&P 500 index futures

This article presents a comprehensive study of continuous time GARCH (generalized autoregressive conditional heteroskedastic) modeling with the thintailed normal and the fat‐tailed Student's‐t and generalized error distributions (GED). The study measures the degree of mean reversion in financial market volatility based on the relationship between discrete‐time GARCH and continuoustime diffusion models. The convergence results based on the aforementioned distribution functions are shown to have similar implications for testing mean reversion in stochastic volatility. Alternative models are compared in terms of their ability to capture mean‐reverting behavior of futures market volatility. The empirical evidence obtained from the S&P 500 index futures indicates that the conditional variance, log‐variance, and standard deviation of futures returns are pulled back to some long‐run average level over time. The study also compares the performance of alternative GARCH models with normal, Student's‐ t, and GED density in terms of their power to predict one‐day‐ahead realized volatility of index futures returns and provides some implications for pricing futures options. © 2008 Wiley Periodicals, Inc. Jrl Fut Mark 28:1–33, 2008     

The quality of volatility traded on the over‐the‐counter currency market: A multiple horizons study

Previous studies of the quality of market‐forecasted volatility have used the volatility that is implied by exchange‐traded option prices. The use of implied volatility in estimating the market view of future volatility has suffered from variable measurement errors, such as the non‐synchronization of option and underlying asset prices, the expiration‐day effect, and the volatility smile effect. This study circumvents these problems by using the quoted implied volatility from the over‐the‐counter (OTC) currency option market, in which traders quote prices in terms of volatility. Furthermore, the OTC currency options have daily quotes for standard maturities, which allows the study to look at the market's ability to forecast future volatility for different horizons. The study finds that quoted implied volatility subsumes the information content of historically based forecasts at shorter horizons, and the former is as good as the latter at longer horizons. These results are consistent with the argument that measurement errors have a substantial effect on the implied volatility estimator and the quality of the inferences that are based on it. © 2003 Wiley Periodicals, Inc. Jrl Fut Mark 23:261–285, 2003     

Memory in returns and volatilities of futures' contracts

Various authors claim to have found evidence of stochastic long‐memory behavior in futures’ contract returns using the Hurst statistic. This paper reexamines futures’ returns for evidence of persistent behavior using a biased‐corrected version of the Hurst statistic, a nonparametric spectral test, and a spectral‐regression estimate of the long‐memory parameter. Results based on these new methods provide no evidence for persistent behavior in futures’ returns. However, they provide overwhelming evidence of long‐memory behavior for the volatility of futures’ returns. This finding adds to the emerging literature on persistent volatility in financial markets and suggests the use of new methods of forecasting volatility, assessing risk, and optimizing portfolios in futures’ markets. © 2000 John Wiley & Sons, Inc. Jrl Fut Mark 20:525–543, 2000     

The new market for volatility trading

This study analyses the new market for trading volatility; VIX futures. We first use market data to establish the relationship between VIX futures prices and the index itself. We observe that VIX futures and VIX are highly correlated; the term structure of average VIX futures prices is upward sloping, whereas the term structure of VIX futures volatility is downward sloping. To establish a theoretical relationship between VIX futures and VIX, we model the instantaneous variance using a simple square root mean‐reverting process with a stochastic long‐term mean level. Using daily calibrated long‐term mean and VIX, the model gives good predictions of VIX futures prices under normal market situation. These parameter estimates could be used to price VIX options. © 2010 Wiley Periodicals, Inc. Jrl Fut Mark 30:809–833, 2010