Forecasting Intraday Volatility and Value-at-Risk with High-Frequency Data

In this paper, we develop modeling tools to forecast Value-at-Risk and volatility with investment horizons of less than one day. We quantify the market risk based on the study at a 30-min time horizon using modified GARCH models. The evaluation of intraday market risk can be useful to market participants (day traders and market makers) involved in frequent trading. As expected, the volatility features a significant intraday seasonality, which motivates us to include the intraday seasonal indexes in the GARCH models. We also incorporate realized variance (RV) and time-varying degrees of freedom in the GARCH models to capture more intraday information on the volatile market. The intrinsic tail risk index is introduced to assist with understanding the inherent risk level in each trading time interval. The proposed models are evaluated based on their forecasting performance of one-period-ahead volatility and Intraday Value-at-Risk (IVaR) with application to the 30 constituent stocks. We find that models with seasonal indexes generally outperform those without; RV can improve the out-of-sample forecasts of IVaR; student GARCH models with time-varying degrees of freedom perform best at 0.5 and 1 % IVaR, while normal GARCH models excel for 2.5 and 5 % IVaR. The results show that RV and seasonal indexes are useful to forecasting intraday volatility and Intraday VaR.     

Deutsche Mark–Dollar Volatility: Intraday Activity Patterns, Macroeconomic Announcements, and Longer Run Dependencies

This paper provides a detailed characterization of the volatility in the deutsche mark–dollar foreign exchange market using an annual sample of five-minute returns. The approach captures the intraday activity patterns, the macroeconomic announcements, and the volatility persistence (ARCH) known from daily returns. The different features are separately quantified and shown to account for a substantial fraction of return variability, both at the intraday and daily level. The implications of the results for the interpretation of the fundamental driving forces behind the volatility process is also discussed.     

Intraday Return Volatility Process: Evidence from NASDAQ Stocks

This paper presents a comprehensive analysis of the distributional and time-series properties of intraday returns. The purpose is to determine whether a GARCH model that allows for time varying variance in a process can adequately represent intraday return volatility. Our primary data set consists of 5-minute returns, trading volumes, and bid-ask spreads during the period January 1, 1999 through March 31, 1999, for a subset of thirty stocks from the NASDAQ 100 Index. Our results indicate that the GARCH(1,1) model best describes the volatility of intraday returns. Current volatility can be explained by past volatility that tends to persist over time. These results are consistent with those of Akgiray (1989) who estimates volatility using the various ARCH and GARCH specifications and finds the GARCH(1,1) model performs the best. We add volume as an additional explanatory variable in the GARCH model to examine if volume can capture the GARCH effects. Consistent with results of Najand and Yung (1991) and Foster (1995) and contrary to those of Lamoureux and Lastrapes (1990), our results show that the persistence in volatility remains in intraday return series even after volume is included in the model as an explanatory variable. We then substitute bid-ask spread for volume in the conditional volatility equation to examine if the latter can capture the GARCH effects. The results show that the GARCH effects remain strongly significant for many of the securities after the introduction of bid-ask spread. Consistent with results of Antoniou, Homes and Priestley (1998), intraday returns also exhibit significant asymmetric responses of volatility to flow of information into the market.     

Testing for Volatility Jumps in the Stochastic Volatility Process

This paper considers the stochastic volatility process with contemporaneous and correlated jumps in returns and volatility, which was proposed by Eraker, B., Johannes, M. and Poison, N. G. (Journal of Finance 53, 2003, 1269--1300) and proposes the Lagrange multiplier test for the presence of jumps in volatility. The test statistic is derived by regarding the degenerate density of volatility jumps with zero variance under the null as Dirac's delta function. The correlation parameter between jumps, which is a nuisance parameter unidentified under the null, is cancelled out in this test statistic and hence the test is free from the Davies problem (Davies, R. B., Biometrika 64, 1977, 247–254).     

Credit Spread Changes and Equity Volatility: Evidence from Daily Data

We investigate the determinants of daily changes in credit spreads in the U.S. corporate bond market. Using a sample of liquid investment grade and high‐yield bonds, we show that both systematic bond and stock market factors as well as idiosyncratic equity market factors affect changes in the yield spread at the daily frequency. In particular, we find that increase in stock market volatility has a positive effect on changes in the spread of corporate bonds over the corresponding Treasuries beyond that captured by standard term structure variables. Our results show that there is an almost contemporaneous inverse relationship between changes in the bond yield spread and the stock return of the issuing firm.     

Intraday Patterns in FX Returns and Order Flow

Using a comprehensive high‐frequency foreign exchange data set, we present evidence of time‐of‐day effects in foreign exchange returns through a significant tendency for currencies to depreciate during local trading hours. We confirm this pattern across a range of currencies and time zones. We also find that this pattern is reflected in order flow and suggest that both patterns relate to the tendency of market participants to be net purchasers of foreign exchange in their own trading hours. Data from a single market maker appears to corroborate that interpretation.     

Dynamic Relationship among Intraday Realized Volatility,Volume and Number of Trades

In this paper, the vector autoregressive model is fitted to find out the causal relationship among realized volatility, the number of transactions and volume with the intraday time intervals of 10, 20 and 30 min. To understand the impact of shock to the market on specific variables, a multivariate Impulse Response Function analysis is also introduced to visualize the causal relationship among the variables. From the analysis of a stock listed on the Stock Exchange of Hong Kong, we find that realized volatility reacts positively to the lagged average trade size. However, the realized volatility forms a negative relationship with the first few lagged number of trades. As a result, the intraday causal relationship among realized volatility, volume and the number of trades is quite different from that obtained on a daily basis. The findings of this paper can enhance the understanding of how the number of trades and the average trade size per transaction affect the risk evolution of financial securities and thus improve the risk management of day trading strategies.     

Trading Returns for the Weekend Effect Using Intraday Data

The existence of the weekend effect has been documented as early as 1885. This paper examines whether the serial dependence in returns around weekends and the magnitude of negative Friday returns can be used to produce superior trading returns. We find some success for this endeavor after accounting for transaction costs (including the bid/ask spread), especially when trading is confined to weekends for which there are large negative Friday returns and to positions opened on Friday afternoons. The effect of stocks trading ex-dividend on Mondays does not appear to bias our results.     

An Analysis of Intraday Patterns in Bid/Ask Spreads for NYSE Stocks

The behavior of time-weighted bid–ask spreads over the trading day are examined. The plot of minute-by-minute spreads versus time of day has a crude reverse J-shaped pattern. Schwartz identifies four determinants of spreads: activity, risk, information, and competition. Using a linear regression model, a significant relationship between these same factors and intraday spreads is demonstrated, but dummy variables for time of day have a reverse J-shape. For given values of the activity, risk, information and competition measures, spreads are higher at the beginning and end of the day relative to the interior period.     

Cyclical Changes in Firm Volatility

We characterize trends and cycles in the volatility of U.S. firms using a measure that we argue more cleanly captures firm‐specific volatility in sales and earnings growth than standard measures do. While earlier literature has emphasized a trend increase in the volatility of publicly traded firms, we find that a typical publicly traded firm has become more stable. We find that the negative association between firm‐specific volatility and the business cycle is weaker than earlier research based on dispersion measures suggests. We find that during the Great Recession of 2007–2009, firm‐specific volatility increased moderately but never substantially exceeded its sample mean. Our results are inconsistent with the hypothesis that firm‐specific volatility is an important driver of the business cycle, as it theoretically could be through an effect of default risk on credit spreads.     

Intraday Patterns in the Cross‐section of Stock Returns

Motivated by the literature on investment flows and optimal trading, we examine intraday predictability in the cross‐section of stock returns. We find a striking pattern of return continuation at half‐hour intervals that are exact multiples of a trading day, and this effect lasts for at least 40 trading days. Volume, order imbalance, volatility, and bid‐ask spreads exhibit similar patterns, but do not explain the return patterns. We also show that short‐term return reversal is driven by temporary liquidity imbalances lasting less than an hour and bid‐ask bounce. Timing trades can reduce execution costs by the equivalent of the effective spread.     

Testing for Serial Correlation in the Presence of Stochastic Volatility

This paper develops a regression-based testing procedure for serial correlation in the presence of stochastic volatility. The asymptotic distribution of the test is derived, and the finite sample properties are investigated. Monte Carlo results shows that the test is reliable in terms of both size and power performances, when the underlying process is a log-linear stochastic volatility. Moreover, the test is superior to Woolridge's (1991) robust LM tests in terms of size in finite sample. Serial correlation tests were conducted for nominal returns of ten exchange rates, and indicated that there is a strong evidence of serial correlation for Yen/Dollar exchange rates.     

Central Bank Actions and Words: The Intraday Effects of FOMC Policy Communications on Individual Equity Volatility and Returns

We compare intraday impacts of the release of Federal Reserve decision announcements and of Federal Open Market Committee minutes between 2004 and 2015 on 1,997 equity return and volatility series. We find that returns are unresponsive to either news release, but conditional volatility increases for both, manifesting immediately after each information release, and persisting for 30 minutes post‐announcement. These effects are larger for decisions than for minutes. On stratifying firms by trading intensity, we find most “high trading intensity” firms respond to these announcements, while “low trading intensity” firms are less affected. Our results show that traders respond, albeit differently, to both sets of information releases.     

Leverage and Volatility Feedback Effects in High-Frequency Data

We examine the relationship between volatility and past andfuture returns using high-frequency aggregate equity index data.Consistent with a prolonged "leverage" effect, we find the correlationsbetween absolute high-frequency returns and current and pasthigh-frequency returns to be significantly negative for severaldays, whereas the reverse cross-correlations are generally negligible.We also find that high-frequency data may be used in more accuratelyassessing volatility asymmetries over longer daily return horizons.Furthermore, our analysis of several popular continuous-timestochastic volatility models clearly points to the importanceof allowing for multiple latent volatility factors for satisfactorilydescribing the observed volatility asymmetries.     

A Note on the Intraday Patterns of Initial Public Offerings: Evidence from Hong Kong

This paper examines the intraday patterns of IPOs in Hong Kong during the period 1995–1998. The results reveal that the well‐known under‐pricing phenomenon of IPOs occurs only at the opening trading of new issues and vanishes afterwards. The return volatility of IPOs is found to be high during the first trading session, and declines rapidly during the rest of the first trading day until the end of the trading day. The intraday return volatility of IPOs is found to follow a double U‐shape pattern, which is similar to that of the general market. A great deal of trading activity was recorded during the first five minutes of the trading day. Consistent results are obtained for IPOs registered during the pre‐crisis and post‐crisis periods. This paper has practical implications for investors. Investors can benefit from the under‐pricing only if they subscribe for new shares in the primary market. There is, however, no profit‐making opportunity for day traders who buy shares on the first trading day. This shows that the Hong Kong market is efficient in adjusting for the IPO under‐pricing. In addition, it is likely that, because of Hong Kong's share allotment method, only big investors who apply for large numbers of shares can benefit from this under‐pricing phenomenon.     

Price Discovery in Chinese Stock Index Futures Market: New Evidence Based on Intraday Data

Using high-frequency data, this study investigates price discovery in the newly established stock index (CSI300) futures market in China. Our empirical results reveal new evidence that the CSI300 index futures market play a dominant role in the price discovery process about one year after its inception and new information is disseminated more rapidly in the stock index futures market than the stock market. This is different from findings in the previous literature. Our results also imply that the index futures market has evolved and can be used as a price discovery vehicle. Thus the CSI300 stock index futures market plays an important role in the capital markets in China.     

Measuring and Testing the Impact of News on Volatility

This paper defines the news impact curve which measures how new information is incorporated into volatility estimates. Various new and existing ARCH models including a partially nonparametric one are compared and estimated with daily Japanese stock return data. New diagnostic tests are presented which emphasize the asymmetry of the volatility response to news. Our results suggest that the model by Glosten, Jagannathan, and Runkle is the best parametric model. The EGARCH also can capture most of the asymmetry; however, there is evidence that the variability of the conditional variance implied by the EGARCH is too high.     

Identifying Monetary Policy Shocks via Changes in Volatility

A central issue of monetary policy analysis is the specification of monetary policy shocks. In a structural vector autoregressive setting there has been some controversy about which restrictions to use for identifying the shocks because standard theories do not provide enough information to fully identify monetary policy shocks. In fact, to compare different theories it would even be desirable to have over-identifying restrictions that would make statistical tests of different theories possible. It is pointed out that some progress toward over-identifying monetary policy shocks can be made by using specific data properties. In particular, it is shown that changes in the volatility of the shocks can be used for identification. Based on monthly U.S. data from 1965 to 1996 different theories are tested and it is found that associating monetary policy shocks with shocks to nonborrowed reserves leads to a particularly strong rejection of the model whereas assuming that the Fed accommodates demand shocks to total reserves cannot be rejected.     

An Examination of Stock Market Return Volatility During Overnight and Intraday Periods, 1964–1989

This paper examines the variance of hourly market returns during 1964–1989. Results indicate that return volatility falls from the opening hour until early afternoon and rises thereafter and is significantly greater for intraday versus overnight periods. Market variance is also shown to change significantly over time, rising after NASDAQ began in 1971, rising after trading in stock options began in 1973, falling after fixed commissions were eliminated in 1975, rising after trading in stock index futures was introduced in 1982, and falling after margin requirements for stock index futures became larger in 1988.     

Volatility Spillovers Between Stock Returns and Exchange Rate Changes: International Evidence

We investigate interdependencies between stock returns and exchange rate changes for six industrialised countries, namely the US, the UK, Japan, Germany, France and Canada, by testing for volatility spillovers using a bivariate EGARCH model. Volatility spillovers from stock returns to exchange rate changes are found for all countries except Germany. These spillovers are symmetric in nature. No evidence is found of volatility spillovers from exchange rate changes to stock returns for any country. Spillovers from stock returns to exchange rate changes have increased since October 1987. This finding is consistent with the notion that international financial markets have become increasingly integrated.