Rate-optimal estimation of mixed semimartingales

Consider the sum of a Brownian motion and an independent fractional Brownian motion with Hurst parameter . Surprisingly, even though is not a semimartingale, Cheridito proved in [Bernoulli 7 (2001) 913--934] that is a semimartingale if . Moreover, is locally equivalent to in this case, so cannot be consistently estimated from local observations of . This paper pivots on a second surprise in this model: if and become correlated, then will never be a semimartingale, and can be identified, regardless of its value. This and other results will follow from a detailed statistical analysis of a more general class of processes called mixed semimartingales, which are semiparametric extensions of with stochastic volatility in both the martingale and the fractional component. In particular, we derive consistent estimators and feasible central limit theorems for all parameters and processes that can be identified from high-frequency observations. We further show that our estimators achieve optimal rates in a minimax sense. The estimation of mixed semimartingales with correlation is motivated by applications to high-frequency financial data contaminated by rough noise.
View on arXiv