Forecasting stock index volatility : comparing implied volatility and the intraday high-low price range

The intraday high–low price range offers volatility forecasts similarly efficient to high-quality implied volatility indexes published by the Chicago Board Options Exchange (CBOE) for four stock market indexes: S&P 500, S&P 100, NASDAQ 100, and Dow Jones Industrials. Examination of in-sample and out-of-sample volatility forecasts reveals that neither implied volatility nor intraday high–low range volatility consistently outperforms the other.

Do retail option traders know better about market volatility?

This paper examines the informational content and predictive power of implied volatility over different forecasting horizons in a sample of European covered warrants traded in the Hong Kong and Singapore markets. The empirical results show that time-series-based volatility forecasts outperform implied volatility forecast as a predictor of future volatility. The finding also suggests that implied volatility is biased and informationally inefficient. The results are attributable to the fact in Hong Kong and Singapore the covered warrants markets are dominated by retail investors, who tend to use covered warrants' leverage to speculate on the price movements of the underlying rather than to express their view on volatility.

Do retail option traders know better about market volatility?

This paper examines the informational content and predictive power of implied volatility over different forecasting horizons in a sample of European covered warrants traded in the Hong Kong and Singapore markets. The empirical results show that time-series-based volatility forecasts outperform implied volatility forecast as predictors of future volatility. The finding also suggests that implied volatility is biased and informationally inefficient and that covered warrants are typically overvalued. The results are attributable to the fact that, in Hong Kong and Singapore, the covered warrants markets are dominated by retail investors who tend to use covered warrants' leverage to speculate on the price movements of the underlying assets rather than to express their view on volatility. Arbitrage is not possible in the markets as short-selling of covered warrants is prohibited.

Load forecasting and neural networks : a prediction interval-based perspective

Successfully determining competitive optimal schedules for electricity generation intimately hinges on the forecasts of loads. The nonstationarity and high volatility of loads make their accurate prediction somewhat problematic. Presence of uncertainty in data also significantly degrades accuracy of point predictions produced by deterministic load forecasting models. Therefore, operation planning utilizing these predictions will be unreliable. This paper aims at developing prediction intervals rather than producing exact point prediction. Prediction intervals are theatrically more reliable and practical than predicted values. The delta and Bayesian techniques for constructing prediction intervals for forecasted loads are implemented here. To objectively and comprehensively assess quality of constructed prediction intervals, a new index based on length and coverage probability of prediction intervals is developed. In experiments with real data, and through calculation of global statistics, it is shown that neural network point prediction performance is unreliable. In contrast, prediction intervals developed using the delta and Bayesian techniques are satisfactorily narrow, with a high coverage probability.

Intraday volatility interaction between the crude oil and equity markets

This paper investigates the price volatility interaction between the crude oil and equity markets in the US using 5-min data over the period 2009-2012. Our main findings can be summarised as follows. First, we find strong evidence to demonstrate that the integration of the bid-ask spread and trading volume factors leads to a better performance in predicting price volatility. Second, trading information, such as bid-ask spread, trading volume, and the price volatility from cross-markets, improves the price volatility predictability for both in-sample and out-of-sample analyses. Third, the trading strategy based on the predictive regression model that includes trading information from both markets provides significant utility gains to mean-variance investors.

Scaling the volatility of credit spreads: evidence from Australian dollar eurobonds

The linear rescaling of the variance of an asset's return is used by many asset pricing models when an annualised risk coefficient is required. However, this approach may not be appropriate for time series, which are not independent and identically distributed (IID). This paper investigates the scaling relationships for daily credit spreads, from January 1995 to May 1998, between AAA-, AA-, and A-rated Australian dollar denominated Eurobonds with maturities of 2, 5, 7, and 10 years. The credit spread return all display similar scaling properties with the estimated standard deviation, based upon a scaling at the square root of time, significantly underestimating the actual level of risk predicted from a normal distribution. These results have implications for risk managers and trading of credit spread instruments.

Structural effects and spillovers in HSIF, HSI and S & P500 volatility

We adopt a BEKK-GARCH framework and employ a systematic approach to jointly examine structural breaks in the Hong Kong cash index and index futures volatility and volatility spillovers from the S&P 500 cash and futures. Multiple switching dummy variables are included in the variance equations to test for any structural changes in the autoregressive volatility structure due to the events that have taken place in the Hong Kong market. Abolishment of the up-tick rule, increase of initial margins and electronic trading of the Hang Seng Index Futures (HSIF) are found to have significant impact when US market spillovers are excluded from a restricted model. Volatility spillovers from the US market are found to have a significant impact and account for some mis-specification in the restricted model.

Simultaneous volatility transmissions and spillover effects: U.S. and Hong Kong stock and futures markets

Contemporaneous transmission effects across volatilities of the Hong Kong Stock and Index futures markets and futures volume of trade are tested by employing a structural systems approach. Competing measures of volatility spillover, constructed from the overnight U.S. S&P500 index futures, are tested and found to impact on the Hong Kong asset return volatility and volume of trade patterns. The examples utilize intra-day 15-min sampled data from this medium-sized Asia Pacific equity and derivative exchange. Both the intra- and inter-day patterns in the Hong Kong market are allowed for in the estimation process.

Regulatory Change v's volume of trade effects in HSIF and HSI volatility

In an earlier paper we adopted a BEKK-GARCH framework and employed a systematic approach to examine structural breaks in the HSIF and HSI volatility. Switching dummy variables were included and tested in the variance equations to check for any structural changes in the autoregressive volatility structure due to the events that have taken place in the Hong Kong market. A Bi-variate GARCH model with 3 switching points was found to be superior as it captured the potential structural changes in return volatilities. Abolishment of the uptick rule, increase of initial margins for the HSIF and electronic trading of HSIF were found to have significant impact on the volatility structure of HSIF and HSI. In this paper we include measures of daily trading volume from both markets in the estimation. Likelihood ratio tests indicate the switching dummy variables become insignificant and the GARCH effects diminish but remain significant.

Regulatory change, structural breaks, and transmission effects in HSIF and HSI volatility

A systematic BEKK-GARCH model with multiple switch points in the variance equations captures the structural changes that have taken place in the Hong Kong markets. Abolishment of the uptick rule in the Hong Kong stock market, increase of initial margins, and electronic trading of Hang Seng Index Futures are found to have significant impacts. These changes affect the volatility structure of the HSI and HSIF and hence their lead-lag relationship. The multivariate GARCH model with three specific switching points is found to be superior to any other combination of up to six separate switch points.

Contemporaneous intra-day volume, option, and futures volatility transmissions across parallel markets

The primary objective of this article is to investigate volatility transmission across three parallel markets operating on the Sydney Futures Exchange (SFE), both within and out of sample. Half-hourly observations are sampled from transaction data for the share price index (SPI) futures, SPI futures options, and 90-day bank accepted bill (BAB) futures markets, and the analysis is carried out using the simultaneous volatility (SVL) system of equations as well as competing volatility models. The results confirm the poor ability of GARCH models to fit intraday data. This study also applies an artificial nesting procedure to evaluate the out-of-sample volatility forecasts. Implied volatility has very limited (if any) predictive power when evaluated in isolation, whereas the SVL model with implied volatility embedded provides incremental information relative to competing model forecasts.

Modelling oil price volatility

In this paper, we examine the volatility of crude oil price using daily data for the period 1991–2006. Our main innovation is that we examine volatility in various sub-samples in order to judge the robustness of our results. Our main findings can be summarised as follows: (1) across the various sub-samples, there is inconsistent evidence of asymmetry and persistence of shocks; and (2) over the full sample period, evidence suggests that shocks have permanent effects, and asymmetric effects, on volatility. These findings imply that the behaviour of oil prices tends to change over short periods of time.