How Often to Sample a Continuous-Time Process in the Presence of Market Microstructure Noise

Classical statistics suggest that for inference purposes one should always use as much data as is available. We study how the presence of market microstructure noise in high-frequency financial data can change that result. We show that the optimal sampling frequency at which to estimate the parameters of a discretely sampled continuous-time model can be finite when the observations are contaminated by market microstructure effects. We then address the question of what to do about the presence of the noise. We show that modelling the noise term explicitly restores the first order statistical effect that sampling as often as possible is optimal. But, more surprisingly, we also demonstrate that this is true even if one misspecifies the assumed distribution of the noise term. Not only is it still optimal to sample as often as possible, but the estimator has the same variance as if the noise distribution had been correctly specified, implying that attempts to incorporate the noise into the analysis cannot do more harm than good. Finally, we study the same questions when the observations are sampled at random time intervals, which are an essential feature of transaction-level data.

[1]  C. Heyde,et al.  Quasi-likelihood and its application , 1997 .

[2]  H. White.  Maximum Likelihood Estimation of Misspecified Models , 1982 .

[3]  Hendrik Bessembinder,et al.  Bid-ask spreads in the interbank foreign exchange markets☆ , 1994 .

[4]  M. Nimalendran,et al.  Price reversals : Bid-ask errors or market overreaction? , 1990 .

[5]  R. Gencay,et al.  Real-Time Trading Models and the Statistical Properties of Foreign Exchange Rates , 1998 .

[6]  M. Nimalendran,et al.  Components of short-horizon individual security returns , 1991 .

[7]  N. Shephard,et al.  Econometric analysis of realized volatility and its use in estimating stochastic volatility models , 2002 .

[8]  Yacine Ait-Sahalia,et al.  The Effects of Random and Discrete Sampling When Estimating Continuous-Time Diffusions , 2002 .

[9]  L. Hansen,et al.  Back to the Future: Generating Moment Implications for Continuous-Time Markov Processes , 1993 .

[10]  Lan Zhang,et al.  A Tale of Two Time Scales , 2003 .

[11]  Gary Gottlieb,et al.  Implications of the Discreteness of Observed Stock Prices , 1985 .

[12]  L. Harris.  Estimation of Stock Price Variances and Serial Covariances from Discrete Observations , 1990 .

[13]  Eric R. Ziegel,et al.  Generalized Linear Models , 2002, Technometrics.

[14]  P. McCullagh.  Tensor Methods in Statistics , 1987 .

[15]  Zhou Zhou,et al.  “A Tale of Two Time Scales: Determining Integrated Volatility with Noisy High-Frequency Data” , 2005 .

[16]  Peter C. B. Phillips,et al.  Fully Nonparametric Estimation of Scalar Diffusion Models , 2001 .

[17]  G. Mason,et al.  Beyond Merton’s Utopia: Effects of Non-normality and Dependence on the Precision of Variance Estimates Using High-frequency Financial Data , 2000 .

[18]  Lawrence Harris,et al.  Statistical Properties of the Roll Serial Covariance Bid/Ask Spread Estimator , 1990 .

[19]  S. Delattre,et al.  A central limit theorem for normalized functions of the increments of a diffusion process, in the presence of round-off errors , 1997 .

[20]  Kuldeep Shastri,et al.  On the Estimation of Bid-Ask Spreads: Theory and Evidence , 1988, Journal of Financial and Quantitative Analysis.

[21]  Laura T. Starks,et al.  Return autocorrelation and institutional investors , 1997 .

[22]  P. Shaman.  ON THE INVERSE OF THE COVARIANCE MATRIX OF A FIRST-ORDER MOVING AVERAGE. , 1969 .

[23]  Maureen O'Hara,et al.  Time and the Process of Security Price Adjustment , 1992 .

[24]  Francis X. Diebold,et al.  Modeling and Forecasting Realized Volatility , 2001 .

[25]  R. C. Merton,et al.  On Estimating the Expected Return on the Market: An Exploratory Investigation , 1980 .

[26]  Lawrence R. Glosten,et al.  Components of the Bid-Ask Spread and the Statistical Properties of Transaction Prices , 1987 .

[27]  Yacine Aït-Sahalia.  Maximum Likelihood Estimation of Discretely Sampled Diffusions: A Closed‐form Approximation Approach , 2002 .

[28]  Lawrence Harris,et al.  Estimating the components of the bid/ask spread , 1988 .

[29]  J. Durbin.  EFFICIENT ESTIMATION OF PARAMETERS IN MOVING-AVERAGE MODELS , 1959 .

[30]  Thomas MaCurdy,et al.  The use of time series processes to model the error structure of earnings in a longitudinal data analysis , 1982 .

[31]  Jonathan D. Cryer,et al.  Time Series Analysis , 1986, Encyclopedia of Big Data.

[32]  J. Jacod,et al.  La Variation Quadratique du Brownien en Pre'sence d''Erreurs d''Arrondi , 1996 .

[33]  Jeffrey R. Russell,et al.  Autoregressive Conditional Duration: A New Model for Irregularly Spaced Transaction Data , 1998 .

[34]  K. French,et al.  Stock return variances: The arrival of information and the reaction of traders , 1986 .

[35]  M. Harrison.  Theories of Abstract Automata. Michael A. Arbib. Prentice-Hall, Englewood Cliffs, N.J., 1969. xviii, 414 pp., illus. $14.95. Prentice-Hall Series in Automatic Computation , 1970 .

[36]  Joel Hasbrouck,et al.  Assessing the Quality of a Security Market: A New Approach to Transaction-Cost Measurement , 1993 .

[37]  Yacine Aït-Sahalia.  Nonparametric Pricing of Interest Rate Derivative Securities , 1995 .

[38]  Jean Jacod,et al.  Diffusions with measurement errors. I. Local Asymptotic Normality , 2001 .

[39]  J. Proudfoot,et al.  Noise , 1931, The Indian medical gazette.

[40]  John N. Haddad.  On the closed form of the likelihood function of the first order moving average model , 1995 .

[41]  A. Lo,et al.  An Econometric Analysis of Nonsynchronous Trading , 1989 .