Results 1 
5 of
5
Separating microstructure noise from volatility
, 2006
"... There are two variance components embedded in the returns constructed using high frequency asset prices: the timevarying variance of the unobservable efficient returns that would prevail in a frictionless economy and the variance of the equally unobservable microstructure noise. Using sample moment ..."
Abstract

Cited by 118 (8 self)
 Add to MetaCart
There are two variance components embedded in the returns constructed using high frequency asset prices: the timevarying variance of the unobservable efficient returns that would prevail in a frictionless economy and the variance of the equally unobservable microstructure noise. Using sample moments of high frequency return data recorded at different frequencies, we provide a simple and robust technique to identify both variance components. In the context of a volatilitytiming trading strategy, we show that careful (optimal) separation of the two volatility components of the observed stock returns yields substantial utility gains.
MICROSTRUCTURE NOISE, REALIZED VARIANCE, AND OPTIMAL SAMPLING
, 2005
"... Observed asset prices are known to deviate from their efficient values due to market microstructure frictions. This paper studies the effects of market microstructure noise on nonparametric estimates of the efficient price integrated variance. Specifically, we consider both asymptotic and finite sam ..."
Abstract

Cited by 89 (9 self)
 Add to MetaCart
Observed asset prices are known to deviate from their efficient values due to market microstructure frictions. This paper studies the effects of market microstructure noise on nonparametric estimates of the efficient price integrated variance. Specifically, we consider both asymptotic and finite sample effects of general market microstructure noise on realized variance estimates. The finite sample results culminate in a variance/bias tradeoff that serves as a basis for an optimal sampling theory. Our theory also considers the effects of prefiltering the data and proposes a novel biascorrection. We show that this theory is easily implementable in practise requiring only the calculation of sample moments of the observable highfrequency return data.
LONGRUN RISKRETURN TRADEOFFS
, 2007
"... Excess market returns are correlated with past market variance. This dependence is statistically mild at short horizons (thereby leading to a hardtodetect riskreturn tradeoff, as in the existing literature) but increases with the horizon and is strong in the long run (i.e., between 6 and 10 years ..."
Abstract

Cited by 4 (0 self)
 Add to MetaCart
Excess market returns are correlated with past market variance. This dependence is statistically mild at short horizons (thereby leading to a hardtodetect riskreturn tradeoff, as in the existing literature) but increases with the horizon and is strong in the long run (i.e., between 6 and 10 years). From an econometric standpoint, we …nd that the longrun predictive power of past market variance is robust to the statistical properties of longhorizon stockreturn predictive regressions. From an economic standpoint, we show that, when conditioning on past market variance, conditional versions of the traditional CAPM and consumptionCAPM yield considerably smaller crosssectional pricing errors than their unconditional counterparts.
Volatility or microstructure noise?
, 2003
"... The notion of realized volatility as a modelfree measurement of the quadratic variation of the underlying log price process loses its asymptotic validity in the presence of market microstructure noise. Should microstructure contaminations be present, the summing of an increasing number of squared r ..."
Abstract

Cited by 2 (0 self)
 Add to MetaCart
The notion of realized volatility as a modelfree measurement of the quadratic variation of the underlying log price process loses its asymptotic validity in the presence of market microstructure noise. Should microstructure contaminations be present, the summing of an increasing number of squared return data (as in the definition of the realized volatility estimator) simply entails increasing accumulation of noise. Using asymptotic arguments as in the extant theoretical literature on the subject, we show that the realized volatility estimator diverges to infinity almost surely when noise plays a role as in a realistic price formation mechanism. We also show that, while the quadratic variation of the log price process cannot be estimated consistently, an appropriately standardized version of the realized volatility estimator can be employed to uncover a specific feature of the noise distribution, namely the second moment of the noise process. 1 1
Microstructure noise, realized volatility, and optimal sampling ∗
, 2003
"... Recorded prices are known to diverge from their “efficient ” values due to the presence of market microstructure contaminations. The microstructure noise creates a dichotomy in the modelfree estimation of integrated volatility. While it is theoretically necessary to sum squared returns that are com ..."
Abstract
 Add to MetaCart
Recorded prices are known to diverge from their “efficient ” values due to the presence of market microstructure contaminations. The microstructure noise creates a dichotomy in the modelfree estimation of integrated volatility. While it is theoretically necessary to sum squared returns that are computed over very small intervals to better indentify the underlying quadratic variation over a period, the summing of numerous contaminated return data entails substantial accumulation of noise. Using asymptotic arguments as in the extant theoretical literature on the subject, we argue that the realized volatility estimator diverges to infinity almost surely when noise plays a role. While realized volatility cannot be a consistent estimate of the quadratic variation of the log price process, we show that a standardized version of the realized volatility estimator can be employed to uncover the second moment of the (unobserved) noise process. More generally, we show that straightforward sample moments of the noisy return data provide consistent estimates of the moments of the noise process. Finally, we quantify the finite sample bias/variance tradeoff that is induced by the accumulation of noisy observations and provide clear and easily implementable directions for optimally sampling contaminated high frequency return data for the purpose of volatility estimation.