Abstract
In this chapter, we present financial high-frequency data and their empirical properties. We discuss data preparation issues and show the statistical properties of various high-frequency variables based on blue chip assets traded at the NYSE, NASDAQ and XETRA. Section 3.1 focuses on peculiar problems which have to be taken into account when transaction data sets are prepared. Section 3.2 discusses the concept of so-called financial durations arising from aggregations based on trading events. Section 3.3 illustrates the statistical features of different types of financial durations including trade durations, price (change) durations and volume durations. In Sect.3.4, we discuss the properties of further trading characteristics such as high-frequency returns, trading volumes, bid-ask spreads and market depth. Section 3.5 presents the empirical features of time aggregated data. Finally, Sect.3.6 gives a compact summary of the major empirical features of high-frequency data.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Strictly speaking, the terminology ”tick data” refers to settings where the data is only recorded whenever the price changes (by at least one tick). The literature is not always stringent with these terminologies.
- 2.
Automatic and efficient limit order book reconstruction can be performed by a limit order book system reconstructor (“LOBSTER”) which is developed at Humboldt-Universität zu Berlin and can be accessed on http://lobster.wiwi.hu-berlin.de.
- 3.
This example was kindly provided by Roel Oomen.
- 4.
Often it is a matter of measurement accuracy that determines whether sub-transactions have exactly the same time stamp or differ only by hundredths of a second.
- 5.
For more details, see Chap. 8.
- 6.
See Chap. 8 for more details on this relationship.
- 7.
Note that these effects are notcaused by split-transactions since such effects have been taken into account already.
- 8.
For more details on the estimation of seasonality effects, see Sect. 5.4.
- 9.
The discontinuities are caused by finite-sample properties as for high aggregation levels the number of underlying observations naturally shrinks.
- 10.
The asymmetries in the distributions are induced by the underlying sample period where, e.g., for JPM, upward price movements are slightly less likely than downward movements.
- 11.
We do not record trade-to-trade midquote changes for Deutsche Telekom since for this stock, we only employ 1-s limit order book snapshots.
- 12.
The ACFs for bid quote changes look very similar and are not shown here.
References
Andersen T, Dobrev D, Schaumburg E (2010) Jump-robust volatility estimation using nearest neighbor truncation Federal Reserve Bank of New York Staff Report, No. 465
Bessembinder H, Panayides M, Venkataraman K (2009) Hidden liquidity: an analysis of order exposure strategies in electronic stock markets. J Finan Econ 94:361–383
Barndorff-Nielsen O, Hansen P, Lunde A, Shephard N (2008b) Realised kernels in practice: trades and quotes. Econom J 4:1–32
Brownlees C, Gallo G (2006) Financial econometric analysis of ultra-high frequency: data handling concerns. Comput Stat Data Anal 51:2232–2245
Finucane TJ (2000) A direct test of methods for inferring trade direction from intra-day data. J Financ QuantAnal 35:553–676
Frey S, Sandas P (2009) The impact of iceberg orders in limit order books. Working Paper 09-06, Centre for Financial Research, Cologne
Grammig J, Wellner M (2002) Modeling the interdependence of volatility and inter-transaction duration process. J Econom 106:369–400
Harris L (2003) Trading & exchanges – market microstructure for practitioners. Oxford University Press, Oxford
Hasbrouck J (2007) Empirical market microstructure. Oxford University Press, Oxford
Hautsch N, Huang R (2009) The market impact of a limit order. Discussion Paper 2009/23, Collaborative Research Center 649 ”Economic Risk”, Humboldt-Universität zu Berlin
Hautsch N, Huang R (2011) On the dark side of the market: identifying and analyzing hidden order placements. Working Paper, Humboldt-Universität zu Berlin
Hautsch N, Kyj L, Oomen R (2011) A blocking and regularization approach to high-dimensional realized covariance estimation. J Appl Econom, in press
Hautsch N, Podolskij M (2010) Pre-averaging based estimation of quadratic variation in the presence of noise and jumps: theory, implementation, and empirical evidence. Discussion Paper 2010/38, Collaborative Research Center 649 ”Economic Risk”, Humboldt-Universität zu Berlin
Henker T, Wang J-X (2006) On the importance of timing specifications in market microstructure research. J Finan Markets 9:162–179
Hansen PR, Lunde A (2006) Realized variance and market microstructure noise. J Bus Econ Stat 24(2):127–161
Lee CMC, Ready MJ (1991) Inferring trade direction from intraday data. J Finance 46:733–746
Roll R (1984) A simple implicit measure of the effective bid-ask spread in an efficient market. J Finance 39:1127–1139
Veredas D, Rodriguez-Poo J, Espasa A (2008) Semiparametric estimation for financial durations. In: Bauwens WPL, Veredas D (eds) High frequency financial econometrics. Physica-Verlag, Heidelberg, pp 225–251
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Hautsch, N. (2012). Empirical Properties of High-Frequency Data. In: Econometrics of Financial High-Frequency Data. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21925-2_3
Download citation
DOI: https://doi.org/10.1007/978-3-642-21925-2_3
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-21924-5
Online ISBN: 978-3-642-21925-2
eBook Packages: Business and EconomicsEconomics and Finance (R0)