Epps Effect Research Articles

Modelling microstructure noise with mutually exciting point processes

We introduce a new stochastic model for the variations of asset prices at the tick-by-tick level in dimension 1 (for a single asset) and 2 (for a pair of assets). The construction is based on marked point processes and relies on mutually exciting stochastic intensities as introduced by Hawkes. We associate a counting process with the positive and negative jumps of an asset price. By suitably coupling the stochastic intensities of upward and downward changes of prices for several assets simultaneously, we can reproduce microstructure noise (i.e. strong microscopic mean reversion at the level of seconds to a few minutes) and the Epps effect (i.e. the decorrelation of the increments in microscopic scales) while preserving standard Brownian diffusion behaviour on large scales. More effectively, we obtain analytical closed-form formulae for the mean signature plot and the correlation of two price increments that enable us to track across scales the effect of the mean-reversion up to the diffusive limit of the model. We show that the theoretical results are consistent with empirical fits on futures Euro–Bund and Euro–Bobl in several situations.

On Epps Effect and Rebalancing of Hedged Portfolio in Multiple Frequencies

Correlations of financial asset returns play a central role in designing investment portfolios by using Markowitz’s modern portfolio theory (MPT). Correlations are calculated from asset prices that happen at various trading time intervals. Therefore, trading frequency dictates correlation values. This phenomenon is called the Epps effect in finance. We present variations of correlations as a function of trading frequency to quantify Epps effect. The results reiterate that portfolio rebalancing, particularly in multiple trading frequencies, requires good estimation of correlations in order to deliver reliable hedging.

A Simple Microstructure Return Model Explaining Microstructure Noise and Epps Effects

We present a simple microstructure model of financial returns that combines (i) the well-known ARFIMA process applied to tick-by-tick returns, (ii) the bid-ask bounce effect, (iii) the fat tail structure of the distribution of returns and (iv) the non-Poissonian statistics of intertrade intervals. This model allows us to explain both qualitatively and quantitatively important stylized facts observed in the statistics of microstructure returns, including the short-ranged correlation of returns, the long-ranged correlations of absolute returns, the microstructure noise and Epps effects. According to the microstructure noise effect, volatility is a decreasing function of the time scale used to estimate it. Paradoxically, the Epps effect states that cross correlations between asset returns are increasing functions of the time scale at which the returns are estimated. The microstructure noise is explained as the result of the negative return correlations inherent in the definition of the bid-ask bounce component (ii). In the presence of a genuine correlation between the returns of two assets, the Epps effect is due to an average statistical overlap of the momentum of the returns of the two assets defined over a finite time scale in the presence of the long memory process (i).

STATISTICAL CAUSES FOR THE EPPS EFFECT IN MICROSTRUCTURE NOISE

We present two statistical causes for the distortion of correlations on high-frequency financial data. We demonstrate that the asynchrony of trades as well as the decimalization of stock prices has a large impact on the decline of the correlation coefficients towards smaller return intervals (Epps effect). These distortions depend on the properties of the time series and are of purely statistical origin. We are able to present parameter-free compensation methods, which we validate in a model setup. Furthermore, the compensation methods are applied to high-frequency empirical data from the NYSE's TAQ database. A major fraction of the Epps effect can be compensated. The contribution of the presented causes is particularly high for stocks that are traded at low prices.

Financial correlations at ultra-high frequency: theoretical models and empirical estimation

A detailed analysis of correlation between stock returns at high frequency is compared with simple models of random walks. We focus in particular on the dependence of correlations on time scales - the so-called Epps effect. This provides a characterization of stochastic models of stock price returns which is appropriate at very high frequency.

High-Frequency Covariance Estimates With Noisy and Asynchronous Financial Data

This article proposes a consistent and efficient estimator of the high-frequency covariance (quadratic covariation) of two arbitrary assets, observed asynchronously with market microstructure noise. This estimator is built on the marriage of the quasi–maximum likelihood estimator of the quadratic variation and the proposed generalized synchronization scheme and thus is not influenced by the Epps effect. Moreover, the estimation procedure is free of tuning parameters or bandwidths and is readily implementable. Monte Carlo simulations show the advantage of this estimator by comparing it with a variety of estimators with specific synchronization methods. The empirical studies of six foreign exchange future contracts illustrate the time-varying correlations of the currencies during the 2008 global financial crisis, demonstrating the similarities and differences in their roles as key currencies in the global market.

Dependence structure of the Korean stock market in high frequency data

This paper analyzes the evolution of the dependence structure for various time window intervals, known as Epps effect, using the Trade and Quote data of 663 actively traded stocks in Korean stock market. It is found that the random matrix theory analysis could not represent the dependence structure of the stock market in the microstructure regime. The Cook–Johnson copula is introduced as a parsimonious alternative method to handle this problem, and the existence of the Epps effect is confirmed for the 663 stocks using high frequency data. It was also found that large capitalization companies tend to have a stronger dependence structure, except for the largest capitalization group, since the phenomenon of price level resistance leads to the weak dependence structure in the largest capitalization group. In addition, grouping the industry as a sub-portfolio is an appropriate approach for hour interval traders, whereas this approach is not a strategy recommended for high frequency traders.

Cross-correlations in volume space: Differences between buy and sell volumes

We study the cross-correlations of buy and sell volumes on the Korean stock market in high frequency. We observe that the pulling effects of volumes are as small as that of returns. The properties of the correlations of buy and sell volumes differ. They are explained by the degree of synchronization of stock volumes. Further, the pulling effects on the minimal spanning tree are studied. In minimal spanning trees with directed links, the large pulling effects are clustered at the center, not uniformly distributed. The Epps effect of buy and sell volumes are observed. The reversal of the cross-correlations of buy and sell volumes is also detected.

The foreign exchange market: return distributions, multifractality, anomalous multifractality and the Epps effect

We present a systematic study of various statistical characteristics of high-frequency returns from the foreign exchange market. This study is based on six exchange rates forming two triangles: EUR–GBP–USD and GBP–CHF–JPY. It is shown that the exchange rate return fluctuations for all of the pairs considered are well described by the non-extensive statistics in terms of q-Gaussians. There exist some small quantitative variations in the non-extensivity q-parameter values for different exchange rates (which depend also on the time scales studied), and this can be related to the importance of a given exchange rate in the world's currency trade. Temporal correlations organize the series of returns such that they develop the multifractal characteristics for all of the exchange rates, with a varying degree of symmetry of the singularity spectrum f(α), however. The most symmetric spectrum is identified for the GBP/USD. We also form time series of triangular residual returns and find that the distributions of their fluctuations develop disproportionately heavier tails as compared to small fluctuations, which excludes description in terms of q-Gaussians. The multifractal characteristics of these residual returns reveal such anomalous properties as negative singularity exponents and even negative singularity spectra. Such anomalous multifractal measures have so far been considered in the literature in connection with diffusion-limited aggregation and with turbulence. Studying the cross-correlations among different exchange rates, we found that market inefficiency on short time scales leads to the occurrence of the Epps effect on much longer time scales, but comparable to the ones for the stock market. Although the currency market is much more liquid than the stock markets and has a much greater transaction frequency, the building up of correlations takes up to several hours—a duration that does not differ much from what is observed in the stock markets. This may suggest that non-synchronicity of transactions is not the unique source of the observed effect.

On EPP effects*

Abstract. In this paper I argue that EPP effects are of two different types, NP‐movement and the Filled Left Edge Effect. While NP‐movement is driven in Narrow Syntax by the computation of Person, some Filled Left Edge phenomena, including Icelandic Stylistic Fronting, seem to take place in PF. Even so, these phenomena also reflect the clausal computation, that is, the matching processes that value clause internal elements in relation to features of the speech event.

Impact of the tick-size on financial returns and correlations

We demonstrate that the lowest possible price change (tick-size) has a large impact on the structure of financial return distributions. It induces a microstructure as well as possibly altering the tail behavior. On small return intervals, the tick-size can distort the calculation of correlations. This especially occurs on small return intervals and thus contributes to the decay of the correlation coefficient towards smaller return intervals (Epps effect). We study this behavior within a model and identify the effect in market data. Furthermore, we present a method to compensate this purely statistical error.

High Frequency Covariance Estimates with Noisy and Asynchronous Financial Data

This paper proposes a consistent and efficient estimator of the high frequency covariance (quadratic covariation) of two arbitrary assets, observed asynchronously with market microstructure noise. This estimator is built upon the marriage of the quasi-maximum likelihood estimator of the quadratic variation and the proposed Generalized Synchronization scheme. It is therefore not influenced by the Epps effect. Moreover, the estimation procedure is free of tuning parameters or bandwidths and readily implementable. The Monte Carlo simulations show the advantage of this estimator by comparing it with a variety of estimators with specific synchronization methods. The empirical studies of six foreign exchange future contracts illustrate the time-varying correlations of the currencies during the global financial crisis in 2008, discovering the similarities and differences in their roles as key currencies in the global market.

Estimating covariation: Epps effect, microstructure noise

This paper is about how to estimate the integrated covariance 〈 X , Y 〉 T of two assets over a fixed time horizon [ 0 , T ] , when the observations of X and Y are “contaminated” and when such noisy observations are at discrete, but not synchronized, times. We show that the usual previous-tick covariance estimator is biased, and the size of the bias is more pronounced for less liquid assets. This is an analytic characterization of the Epps effect. We also provide the optimal sampling frequency which balances the tradeoff between the bias and various sources of stochastic error terms, including nonsynchronous trading, microstructure noise, and time discretization. Finally, a two scales covariance estimator is provided which simultaneously cancels (to first order) the Epps effect and the effect of microstructure noise. The gain is demonstrated in data.

Compensating asynchrony effects in the calculation of financial correlations

We present a method to compensate statistical errors in the calculation of correlations on asynchronous time series. The method is based on the assumption of an underlying time series. We set up a model and apply it to financial data to examine the decrease of calculated correlations towards smaller return intervals (Epps effect). We show that the discovered statistical effect is a major cause of the Epps effect. Hence, we are able to quantify and to compensate it using only trading prices and trading times.

MULTISCALED CROSS-CORRELATION DYNAMICS IN FINANCIAL TIME-SERIES

The cross-correlation matrix between equities comprises multiple interactions between traders with varying strategies and time horizons. In this paper, we use the Maximum Overlap Discrete Wavelet Transform to calculate correlation matrices over different time–scales and then explore the eigenvalue spectrum over sliding time-windows. The dynamics of the eigenvalue spectrum at different times and scales provides insight into the interactions between the numerous constituents involved. Eigenvalue dynamics are examined for both medium, and high-frequency equity returns, with the associated correlation structure shown to be dependent on both time and scale. Additionally, the Epps effect is established using this multivariate method and analyzed at longer scales than previously studied. A partition of the eigenvalue time-series demonstrates, at very short scales, the emergence of negative returns when the largest eigenvalue is greatest. Finally, a portfolio optimization shows the importance of time–scale information in the context of risk management.

The Epps effect revisited

We analyse the dependence of stock return cross-correlations on the data sampling frequency, known as the Epps effect: for high-resolution data the cross-correlations are significantly smaller than their asymptotic value as observed for daily data. The former description implies that a changing trading frequency should alter the characteristic time of the phenomenon. This is not true for empirical data: the Epps curves do not scale with market activity. The latter result indicates that the time scale of the phenomenon is related to the reaction time of market participants (this we denote as the human time scale), independent of market activity. In this paper we give a new description of the Epps effect through the decomposition of cross-correlations. After testing our method on a model of generated random walk price changes we justify our analytical results by fitting the Epps curves of real-world data.

On the origin of the Epps effect

The Epps effect, the decrease of correlations between stock returns for short time windows, was traced back to the trading asynchronicity and to the occasional lead-lag relation between the prices. We study pairs of stocks where the latter is negligible and confirm the importance of asynchronicity but point out that alone these aspects are insufficient to give account for the whole effect.

Increasing market efficiency: Evolution of cross-correlations of stock returns

We analyse the temporal changes in the cross-correlations of returns on the New York Stock Exchange. We show that lead–lag relationships between daily returns of stocks vanished in less than 20 years. We have found that even for high-frequency data the asymmetry of time-dependent cross-correlation functions has a decreasing tendency, the position of their peaks is shifted towards the origin while these peaks become sharper and higher, resulting in a diminution of the Epps effect. All these findings indicate that the market becomes increasingly efficient.

Time scales involved in emergent market coherence

In addressing the question of the time scales characteristic for the market formation, we analyze high-frequency tick-by-tick data from the NYSE and from the German market. By using returns on various time scales ranging from seconds or minutes up to 2 days, we compare magnitude of the largest eigenvalue of the correlation matrix for the same set of securities but for different time scales. For various sets of stocks of different capitalization (and the average trading frequency), we observe a significant elevation of the largest eigenvalue with increasing time scale. Our results from the correlation matrix study can be considered as a manifestation of the so-called Epps effect. There is no unique explanation of this effect and it seems that many different factors play a role here. One of such factors is randomness in transaction moments for different stocks. Another interesting conclusion to be drawn from our results is that in the contemporary markets the emergence of significant correlations occurs on time scales much smaller than in the more distant history.

A CLOSER LOOK AT THE EPPS EFFECT

Epps [17] reported empirical evidence that stock correlations decrease when sampling frequency increases. This phenomenon, named Epps effect, has been observed in several markets. In this paper, the dynamics underlying the Epps effect are investigated. Using Monte Carlo simulations and the analysis of high frequency foreign exchange rate and stock price data, it is shown that the Epps effect can largely be explained by two factors: the non-synchronicity of price observations and the existing lead-lag relationship between asset prices. In order to compute co-volatilities, an original method based upon the Fourier analysis is adopted. This method performs well in estimating correlations precisely, as illustrated by simulated experiments. Being naturally embedded in the frequency domain, this estimator is well suited to the study of the Epps effect.