Fourier transform methods for pathwise covariance estimation in the presence of jumps

TL;DR

This paper introduces a non-parametric Fourier-based method for estimating the path of instantaneous covariance in multidimensional financial data, effectively handling jumps and improving estimation accuracy.

Contribution

It extends Fourier methods for covariance estimation to jump processes, providing a consistent, robust estimator with a smaller asymptotic variance and practical calibration applications.

Findings

Estimator has smaller asymptotic variance by 2/3 compared to classical methods.

Method is robust and allows iterative estimation of stochastic covariance.

Successfully applied to multivariate financial modeling and calibration.

Abstract

We provide a new non-parametric Fourier procedure to estimate the trajectory of the instantaneous covariance process (from discrete observations of a multidimensional price process) in the presence of jumps extending the seminal work Malliavin and Mancino~\cite{MM:02, MM:09}. Our approach relies on a modification of (classical) jump-robust estimators of integrated realized covariance to estimate the Fourier coefficients of the covariance trajectory. Using Fourier-F\'ejer inversion we reconstruct the path of the instantaneous covariance. We prove consistency and central limit theorem (CLT) and in particular that the asymptotic estimator variance is smaller by a factor $ 2/3$ in comparison to classical local estimators. The procedure is robust enough to allow for an iteration and we can show theoretically and empirically how to estimate the integrated realized covariance of the instantaneous stochastic covariance process. We apply these techniques to robust calibration problems for multivariate modeling in finance, i.e., the selection of a pricing measure by using time series and derivatives' price information simultaneously.