“A Tale of Two Time Scales: Determining Integrated Volatility with Noisy High-Frequency Data”

It is common practice in finance to estimate volatility from the sum of frequentlysampled squared returns. However, market microstructure poses challenges to this estimation approach, as evidenced by recent empirical studies in finance. I will talk briefly about the present work on how to lay out theoretical grounds that reconcile continuous-time modeling and discrete-time samples. I will mention why and where the ‘usual’ volattility estimator fails when the returns are sampled at the highest frequencies. If the noise is asymptotically small, recent work provides a way of finding the optimal sampling frequency. A better approach, the ‘two scales estimator’, works for any size of the noise.