High Frequency Data

We use an agent-based approach to model trading behaviour in high-frequency markets. This study focuses on the Foreign Exchange (FX) market. The initial part of this study is to observe the micro-behaviour of traders to define the stylized facts of their trading activities. This is performed using a high- frequency dataset of anonymised individual traders' historical transactions on an account

We examine the relationship between volatility and past and future returns using high-frequency aggregate equity index data. Consistent with a prolonged “leverage” effect, we find the correlations between absolute high-frequency returns and current and past high-frequency returns to ...

Growth forecasts are at the heart of investment decisions and yet in emerging and developing markets they often receive limited support from quantitative models. This paper describes the main quantitative modelling techniques that have informed EBRD growth projections since 2009. The paper describes how bridge models use high-frequency data and the generalised dynamic factor model uses a vast body of cross-country data to nowcast growth. In addition, a Bayesian vector-autoregressive model is used to forecast growth under various scenarios. The paper includes a comparison between the forecasting performance of the model and that of economists, the latter working both at the EBRD and at other institutions. Osterholm for their comments and suggestions. We also thank Jeromin Zettelmeyer for sharing the Matlab version of the Bayesian VAR model with us. The working paper series has been produced to stimulate debate on the economic transformation of central and eastern Europe and the CIS. ...

After excluding countries with high-inflation crisesperiods and Long-Run Growth when annual inflation is above 40 percentthe data reveal no evidence of a Michael Bruno William Easterly consistent relationship between growth and inflation, at any frequency. But growth does tend to fall sharply during discrete crises of high inflation and to recover surprisingly strongly after inflation falls. Perhaps inflation crises are purely cyclical, or perhaps in the long run they have a favorable purgative effect. Abstract Recent literature suggests that long-run averages of growth and inflation are only weakly correlated and such correlation is not robust to exclusion of extreme inflation observations; inclusion of time series panel data has improved matters but an aggregate parametric approach remains inconclusive. We propose a nonparametric definition of high inflation crises as periods when inflation is above 40 percent annual. Ercluding countries with high inflation crises, we find no evidence of any consistent relationship between growth and inflation at any frequency. However, we find that growth falls sharply during discrete high inflation crises, then recovers surprisingly strongly after inflation falls. The fall in growth during crisis and recovery of growth after crisis tend to average out to close to zero (even slightly above zero), hence the lack of a robust cross-section correlation. Our findings could be consistent either with trend stationarity of output, in which inflation crises are purely cyclical phenomena, or with models in which crises have a favorable long-run purgative effect. Our findings do not support the view that reduction of high inflation carries heavy short-to-medium run output costs.

Analyzing co-movements in equity markets is important for risk diversification in portfolio management. Copulas have several advantages compared to the linear correlation measure in modeling co-movement. This paper introduces a copula ARMA-GARCH model for analyzing the co-movement of indexes in German equity markets. The model is implemented with an ARMA-GARCH model for the marginal distributions and a copula for the joint distribution. After goodness of fit testing, we find that the skewed Student's t copula ARMA(1,1)-GARCH(1,1) model with Lévy fractional stable noise is superior to alternative models investigated in our study where we model the simultaneous co-movement of six German equity market indexes. This model is also suitable for capturing the long-range dependence, tail dependence, asymmetric correlation observed in German equity markets.

With the availability of intra-daily price data, researchers have focused more attention on market microstructure issues to understand and help formulate strategies for the timing of trades. The purpose of this article is to provide a brief survey of the research employing intra-daily price data. Specifically, we review stylized facts of intra-daily data, econometric issues of data analysis, application of intra-daily data in volatility and liquidity research, and the applications to market microstructure theory. Long-range dependence is observed in intra-daily data. Because fractal processes or fractional integrated models are usually used to model long-range dependence, we also provide a review of fractal processes and long-range dependence in order to consider them in future research using intra-daily data.

The sum of squared intraday returns provides an unbiased and almost errorfree measure of ex-post volatility. In this paper we develop a nonlinear Autoregressive Fractionally Integrated Moving Average (ARFIMA) model for realized volatility, which accommodates level shifts, day-of-the-week effects, leverage effects and volatility level effects. Applying the model to realized volatilities of the S&P 500 stock index and three exchange rates produces forecasts that clearly improve upon the ones obtained from a linear ARFIMA model and from conventional time-series models based on daily returns, treating volatility as a latent variable.

Spot foreign exchange market today is the most volatile and liquid of all financial markets in the world. The present paper addresses in details the efficiency, liquidity and risk seen by a trader, particularly concentrating on analysis of high frequency data for intraday trading. The main findings of the research include the fact that the market was found to be efficient in weak form, which in particular means that technical analysis cannot be successfully applied to systematically get an above average profit from speculative trades, but fundamental analysis may increase the expected income. Carry trades were not found to be consistently profitable or generating non negative profit. Spot foreign exchange market was proven to be extremely liquid, and its liquidity is being independent from regional trading sessions. We also found no evidence on the spot forex market of hot potato trading that usually follows news announcements. Finally, five different risk measures have shown that t...

This report covers the important topic of stochastic volatility modelling with an emphasis on linear state models. The approach taken focuses on comparing models based on their ability to flt the data and their forecasting performance. To this end several parsimonious stochastic volatility models are estimated using realised volatility, a volatility proxy from high frequency stock price data. The

Lake Analyzer is a numerical code coupled with supporting visualization tools for determining indices of mixing and stratification that are critical to the biogeochemical cycles of lakes and reservoirs. Stability indices, including Lake Number, Wedderburn Number, Schmidt Stability, and thermocline depth are calculated according to established literature definitions and returned to the user in a time series format. The program was created for the analysis of high-frequency data collected from instrumented lake buoys, in support of the emerging field of aquatic sensor network science. Available outputs for the Lake Analyzer program are: water temperature (error-checked and/or down-sampled), wind speed (errorchecked and/or down-sampled), metalimnion extent (top and bottom), thermocline depth, friction velocity, Lake Number, Wedderburn Number, Schmidt Stability, mode-1 vertical seiche period, and Brunt-Väisälä buoyancy frequency. Secondary outputs for several of these indices delineate the parent thermocline depth (seasonal thermocline) from the shallower secondary or diurnal thermocline. Lake Analyzer provides a program suite and best practices for the comparison of mixing and stratification indices in lakes across gradients of climate, hydro-physiography, and time, and enables a more detailed understanding of the resulting biogeochemical transformations at different spatial and temporal scales.

The goal of this paper is twofold. First, using five of the most actively traded stocks in the Brazilian financial market, this paper shows that the normality assumption commonly used in the risk management area to describe the distributions of returns standardized by volatilities is not compatible with volatilities estimated by EWMA or GARCH models. In sharp contrast, when the information contained in high frequency data is used to construct the realized volatility measures, we attain the normality of the standardized returns, giving ...

The objective of this paper is to investigate the use of tick-by-tick data for market risk measurement. We propose an Intraday Value at Risk (IVaR) at different horizons based on irregularly time-spaced high-frequency data by using an intraday Monte Carlo simulation. An UHF-GARCH model extending the framework of Engle is used to specify the joint density of the marked-point process of durations and high-frequency returns. We apply our methodology to transaction data for the Royal Bank and the Placer Dome stocks traded on the Toronto Stock Exchange. Results show that our approach constitutes reliable means of measuring intraday risk for traders who are very active on the market. The UHF-GARCH model performs well out-ofsample for almost all the time horizons and the confidence levels considered even when normality is assumed for the distribution of the error term, provided that intraday seasonality has been accounted for prior to the estimation.

This paper evaluates the performance of conditional variance models using high-frequency data of the National Stock Index (S&P CNX NIFTY) and attempts to determine the optimal sampling frequency for the best daily volatility forecast. A linear combination of the realized volatilities calculated at two different frequencies is used as benchmark to evaluate the volatility forecasting ability of the conditional variance models (GARCH (1, 1)) at different sampling frequencies. From the analysis, it is found that sampling at 30 minutes gives the best forecast for daily volatility. The forecasting ability of these models is deteriorated, however, by the non-normal property of mean adjusted returns, which is an assumption in conditional variance models. Nevertheless, the optimum frequency remained the same even in the case of different models (EGARCH and PARCH) and different error distribution (generalized error distribution, GED) where the error is reduced to a certain extent by incorporating the asymmetric effect on volatility. Our analysis also suggests that GARCH models with GED innovations or EGRACH and PARCH models would give better estimates of volatility with lower forecast error estimates. Copyright pricing, portfolio decisions and risk management through calculation of value at risk (VaR). There have been many proposed ways of measuring the volatility of asset prices. A simple static estimate, called historical volatility, has been used for a long time. Contemporary research in volatility modeling was motivated by the pioneering work of Engle (1982) on ARCH. Engle established the basic idea of modeling volatility as a time-varying function of the current information. The family of GARCH models was later introduced by Bollerslev (1986), and also discussed independently by . The GARCH(1, 1) model remains the workhorse in the GARCH family. These models have been extensively used in studying volatility clusters in fi nancial time series . There is another class of dynamic volatility models, which are based on the basic assumption that the volatility is stochastic. These are called stochastic volatility (SV) models (see .

The increased episodes of the financial crises throughout the world in the 1990s motivated research interests to identify the channels through which such crises spread from one country to the entire region and across regions and to suggest policies to avoid the worst of such crises. Researchers have identified several factors that may spark and induce contagion of the crisis. Strong trade and financial market linkages may contribute to contagion of the crises. This also implies that, even economies with strong fundamentals could not escape contagion. This study attempts to identify and trace the alleged origin and the subsequent path of the currency contagion using data from a sample of selected Asian countries. For empirical estimation, we use high frequency data (daily observation) on exchange rates from 1994 to 2002. We split the sample in to four periods (full, pre -crisis, crisis and post-crisis periods), construct a multivariate GARCH model and apply Granger causality test to ...

This article examines the impact of serial correlation in high frequency returns on the realized variance measure. In particular, it is shown that the realized variance measure yields a biased estimate of the conditional return variance when returns are serially correlated. Using 10 years of FTSE-100 minute by minute data we demonstrate that a careful choice of sampling frequency is crucial in avoiding substantial biases. Moreover, we find that the autocovariance structure (magnitude and rate of decay) of FTSE-100 returns at different sampling frequencies is consistent with that of an ARMA process under temporal aggregation. A simple autocovariance function based method is proposed for choosing the "optimal" sampling frequency, that is, the highest available frequency at which the serial correlation of returns has a negligible impact on the realized variance measure. We find that the logarithmic realized variance series of the FTSE-100 index, constructed using an optimal sampling frequency of 25 minutes, can be modelled as an ARFIMA process. Exogenous variables such as lagged returns and contemporaneous trading volume appear to be highly significant regressors and are able to explain a large portion of the variation in daily realized variance.

In this work we deal with the design and simulation of a complete multi-carrier modem alternative to the recommended one (single-carrier) for the high frequency data link standard (known as HFDL) for communications between ground stations and civil aircraft. We show how the multicarrier modem offers a better performance, from the bit error rate point of view, even in the case of very short interleaving procedure, fulfilling, at the same time, the timing constraints imposed by the TDMA structure of the HFDL system

Analyzing co-movements in equity markets is important for risk diversification in portfolio management. Copulas have several advantages compared to the linear correlation measure in modeling co-movement. This paper introduces a copula ARMA-GARCH model for analyzing the co-movement of indexes in German equity markets. The model is implemented with an ARMA-GARCH model for the marginal distributions and a copula for the joint distribution. After goodness of fit testing, we find that the skewed Student's t copula ARMA(1,1)-GARCH(1,1) model with Lévy fractional stable noise is superior to alternative models investigated in our study where we model the simultaneous co-movement of six German equity market indexes. This model is also suitable for capturing the long-range dependence, tail dependence, asymmetric correlation observed in German equity markets.

A rapidly growing literature has documented important improvements in financial return volatility measurement and forecasting via use of realized variation measures constructed from high-frequency returns coupled with simple modeling procedures. Building on recent theoretical results in Barndorff-Nielsen and Shephard (2004a, 2005) for related bi-power variation measures, the present paper provides a practical and robust framework for non-parametrically measuring the jump component in asset return volatility. In an application to the DM/$ exchange rate, the S&P500 market index, and the 30-year U.S. Treasury bond yield, we find that jumps are both highly prevalent and distinctly less persistent than the continuous sample path variation process. Moreover, many jumps appear directly associated with specific macroeconomic news announcements. Separating jump from non-jump movements in a simple but sophisticated volatility forecasting model, we find that almost all of the predictability in daily, weekly, and monthly return volatilities comes from the non-jump component. Our results thus set the stage for a number of interesting future econometric developments and important financial applications by separately modeling, forecasting, and pricing the continuous and jump components of the total return variation process.

This paper uses high-frequency data to examine the relation between official and free-market exchange rates in Albania. We use daily data to test econometrically, first, whether the official and free markets are efficient, in the sense that one cannot use exchange rate movements denominated in one currency to predict movements in another currency, and second, whether movements in the free-market rate "cause" movements in the official rate. Our results provide support for the first proposition and partial support for the second. We also report the results of a unique survey of free-market dealers in Tirana, designed to determine the main factors that influence exchange rate movements. The evidence is that country-specific factors, in particular the large flows of illegal smuggling and emigrants' remittances, are more important than fluctuations in the international exchange market. JEL Classification: F31, O17

rnCJflqJU © UOtCC ! !1n tO tJJ 2OfltC to cxcccq uo bibp urn?t pc dnotcq tpont cxbpcp bcuinou bLoAiqcq tpt jrijj ci.cq © JÔÔ P N!CP! BWUO ruq fiJJJW EtLP VII L!PL2 LL!f 2POLt GC1OU2 O tcxt not QxbLQ22q qJO O tJJC rI1JJOL2 mq UOt tJJO2C O tJJQ Wt!0U9J B" O ECOUOUJ!C J{G2CLCJJ J4BEL LCLC bLomuJ u Iiuci.n1!OuuJ uucc nq NCLOGCOUOUJ!C VIA ob!n!ou Jp Ixthci. bn.t o Lcctcp iwncc jpc qwt OL tp bbcL cu G qo/fnJoqGq on tpc iutcut t ipc PA BOOt uq tJC J4C!A CjJOOJ O ECOUOUJC !IJ N0OE JC LC uqcptcq to G!flbbC OL DcAcJobwcuf BuJ wc r'tu vurz.!cu on cucc on ECOUOUJ! yoitp in tjJ flUTA12IA O /2p!IJtoU tJJ flhJiAGI2t? O BL!t!2P COIn UJp ipc ujc o tpc bn.ncibmt n uiprnI2 t qJc I4BE! NOUCWLA ECOUOUJJC 2IIIJJWGL PJt!Wt tIJ jOLJq BUT nwi3d qirlanolfsbi lsnoiionul otnolonom '(118 01 .a1i3BITI noilsilni i1ir1 '((no [l3irfw

It is generally believed that for the power of unit root tests, only the time span and not the observation frequency matters. In this paper we show that the observation frequency does matter when the high-frequency data display fat tails and volatility clustering, as is typically the case for nancial time series such as exchange rate returns. Our claim builds on recent work on unit root and cointegration testing based non-Gaussian likelihood functions. The essential idea is that such methods will yield power gains in the presence of fat tails and persistent volatility clustering, and the strength of these features (and hence the power gains) increases with the observation frequency. This is illustrated using both Monte Carlo simulations and empirical applications to real exchange rates.

A rapidly growing literature has documented important improvements in volatility measurement and forecasting performance through the use of realized volatilities constructed from highfrequency returns coupled with relatively simple reduced-form time series modeling procedures. Building on recent theoretical results from Barndorff-Nielsen and Shephard (2003c,d) for related bipower variation measures involving the sum of high-frequency absolute returns, the present paper provides a practical framework for non-parametrically measuring the jump component in realized volatility measurements. Exploiting these ideas for a decade of high-frequency five-minute returns for the DM/$ exchange rate, the S&P500 market index, and the 30-year U.S. Treasury bond yield, we find the jump component of the price process to be distinctly less persistent than the continuous sample path component. Explicitly including the jump measure as an additional explanatory variable in an easy-toimplement reduced form model for realized volatility results in highly significant jump coefficient estimates at the daily, weekly and quarterly forecast horizons. As such, our results hold promise for improved financial asset allocation, risk management, and derivatives pricing, by separate modeling, forecasting and pricing of the continuous and jump components of total return variability. that the conditional variance of many assets is best described by a combination of a smooth and very slowly mean-reverting continuous sample path process, along with a much less persistent jump component.

We show how pre-averaging can be applied to the problem of measuring the ex-post covariance of financial asset returns under microstructure noise and non-synchronous trading. A pre-averaged realised covariance is proposed, and we present an asymptotic theory for this new estimator, which can be configured to possess an optimal convergence rate or to ensure positive semi-definite covariance matrix estimates. We also derive a noise-robust Hayashi-Yoshida estimator that can be implemented on the original data without prior alignment of prices. We uncover the finite sample properties of our estimators with simulations and illustrate their practical use on high-frequency equity data.

Development and Testing of an Information Monitoring and Diagnostics System for Large Commercial Buildings Mary Ann Piette , Lisa Gartland, Satkartar Khalsa, Lawrence Berkeley National Laboratory, Berkeley, CA Peter Rumsey and Lee Eng Lock, Supersymmetry, Oakland CA and Singapore Anthony Sebald, University Of California, San Diego, CA Christine Shockman, Stanford University, Palo Alto, CA ABSTRACT Large commercial buildings generally do not operate at economically achievable levels of energy efficiency. Performance monitoring projects have shown whole-building energy savings of 20% or more through improved operation and maintenance practices. The opportunity for O&M savings is related to systemic problems associated with the lack of feedback available from current Energy Management and Control Systems (EMCS). Today’s EMCS are designed for control, with limited capabilities in sensing, archiving, data analysis, diagnostics, and data visualization. This paper discusses a multi- year, ...

This document is the property of Olsen Ltd. and is proprietary and confidential. It is not permitted to disclose, copy or distribute the document except by written permission of Olsen Ltd. ... 3.4 Bias Correction of high frequency partial volatilities forecasts . . . . . . . . . . . . . . . .

The causal impact of algorithmic trading (AT) on market quality is difficult to establish due to endogeneity bias. We address this problem by using the introduction of co-location as an exogenous event after which AT increased. Matching techniques are used to identify a matched set of firms with high and low AT to estimate causal impact. We find that securities with higher AT have lower liquidity costs, order imbalance, and price volatility. We find new evidence that high AT is not associated with higher intraday liquidity risk or higher incidence of extreme intraday price movements.

In this paper we propose a new lossless image compression method. The suggested method relies on novel selective scan process that aims to scan the image in the direction where minimal pixel intensity change is recorded. Such scan process would reduce high frequency data, in order to provide a smooth and high correlated mono-dimensional signal easy to compress. This scan process is followed by an adapted coding scheme based on DPCM and Huffman algorithms. The experimental results show a significant compression improvement of the suggested method as compared to two common lossless coders in the same class.

Analyzing co-movements in equity markets is important for risk diversification in portfolio management. Copulas have several advantages compared to the linear correlation measure in modeling co-movement. This paper introduces a copula ARMA-GARCH model for analyzing the co-movement of indexes in German equity markets. The model is implemented with an ARMA-GARCH model for the marginal distributions and a copula for the joint distribution. After goodness of fit testing, we find that the skewed Student's t copula ARMA(1,1)-GARCH(1,1) model with Lévy fractional stable noise is superior to alternative models investigated in our study where we model the simultaneous co-movement of six German equity market indexes. This model is also suitable for capturing the long-range dependence, tail dependence, asymmetric correlation observed in German equity markets.

The objective of this paper is to investigate the use of tick-by-tick data for market risk measurement. We propose an Intraday Value at Risk (IVaR) at different horizons based on irregularly time-spaced high-frequency data by using an intraday Monte Carlo simulation. An UHF-GARCH model extending the framework of Engle is used to specify the joint density of the marked-point process of durations and high-frequency returns. We apply our methodology to transaction data for the Royal Bank and the Placer Dome stocks traded on the Toronto Stock Exchange. Results show that our approach constitutes reliable means of measuring intraday risk for traders who are very active on the market. The UHF-GARCH model performs well out-ofsample for almost all the time horizons and the confidence levels considered even when normality is assumed for the distribution of the error term, provided that intraday seasonality has been accounted for prior to the estimation.

Using a data set consisting of three years of 5-minute intraday stock index returns for major European stock indices and U.S. macroeconomic surprises, the conditional mean and volatility behaviors in European market were investigated. The findings suggested that the opening of the U.S market significantly raised the level of volatility in Europe, and that all markets respond in an identical fashion. Furthermore, the U.S. macroeconomic surprises exerted an immediate and major impact on both European stock markets' returns and volatilities. Thus, high frequency data appear to be critical for the identification of news that impacted the markets.

This paper characterizes the temporal pattern of trading rule returns and official intervention for Australian, German, Swiss and U.S. data to investigate whether intervention generates technical trading rule profits. High frequency data show that abnormally high trading rule returns precede German, Swiss and U.S. intervention, disproving the hypothesis that intervention generates inefficiencies from which technical rules profit. Australian intervention precedes high trading rule returns, but trading/intervention patterns make it implausible that intervention actually generates those returns. Rather, intervention responds to exchange rate trends from which trading rules have recently profited.

This paper applies an established bid-ask spread decomposition model to the interdealer spot foreign exchange market. In addition, the paper presents and tests a modified decomposition model which is specifically adapted to the features of order-driven markets and which is found to produce more plausible results than the original model. Price clustering is introduced as a new explanatory factor within this framework and is shown to be vitally important in understanding the composition of bid-ask spreads in this market.