Jump-robust estimation of volatility with simultaneous presence of microstructure noise and multiple observations (Q522057)

The author develops multipower estimators for the integrated volatility \(\int_0^t \sigma^2_s ds\). These estimators allow the presence of jumps in the underlying driving process and the simultaneous presence of microstructure noise and multiple records of observations (more than one observation recorded on a single time stamp) as often seen in stock markets for heavily traded securities with a data set with even millisecond frequency. Consistency and asymptotic normality of the estimators for both noise-free and noise-present cases are established and the estimators are applied to a real high-frequency data set.