Laws of large numbers for Hayashi–Yoshida-type functionals

Abstract

In high-frequency statistics and econometrics sums of functionals of increments of stochastic processes are commonly used and statistical inference is based on the asymptotic behaviour of these sums as the mesh of the observation times tends to zero. Inspired by the famous Hayashi-Yoshida estimator for the quadratic covariation process based on two asynchronously observed stochastic processes we investigate similar sums based on increments of two asynchronously observed stochastic processes for general functionals. We find that our results differ from corresponding results in the setting of equidistant and synchronous observations which has been well studied in the literature. Further we observe that in the setting of asynchronous observations the asymptotic behaviour is not only determined by the nature of the functional but also depends crucially on the asymptotics of the observation scheme.

ETF Basket-Adjusted Covariance estimation

“…Although there is a vast literature (see Jacod and Rosenbaum, 2013, Li et al, 2016, Li et al, 2019, Hayashi et al, 2011, Martin and Vetter, 2019, and the references therein) on the estimation of volatility functionals of the form ∫ 1 0 g(Σ s )ds where g is a deterministic function, to the best of our knowledge, none of the available results can be applied to our situation, which requires a random transformation of the spot volatility. This situation is investigated in this subsection in the absence of microstructure noise and under the following assumption on the observation times:…”