A remark on the rates of convergence for integrated volatility estimation in the presence of jumps

Abstract

The optimal rate of convergence of estimators of the integrated volatility, for a discontinuous Itô semimartingale sampled at regularly spaced times and over a fixed time interval, has been a long-standing problem, at least when the jumps are not summable. In this paper, we study this optimal rate, in the minimax sense and for appropriate "bounded" nonparametric classes of semimartingales. We show that, if the $r$th powers of the jumps are summable for some $r\in [0,2)$, the minimax rate is equal to $\min (\sqrt{n},(n\log n{)}^{(2-r)/2})$, where $n$ is the number of observations.

Published in at http://dx.doi.org/10.1214/13-AOS1179 the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)

Cited by in corpus (9)

• Quarticity and other functionals of volatility: Efficient estimation
• Efficient estimation of integrated volatility in presence of infinite variation jumps
• Volatility occupation times
• Near-optimal estimation of jump activity in semimartingales
• High-frequency Donsker theorems for Lévy measures
• Estimating time-changes in noisy Lévy models
• Estimation of state-dependent jump activity and drift for Markovian semimartingales
• Recovering Brownian and jump parts from high-frequency observations of a Lévy process
• Testing the characteristics of a Lévy process