Photo by _louisreed from unsplash
We define a non-parametric estimator of the leverage effect by means of the covariance between the asset return and its volatility. The data are assumed to follow a stochastic volatility… Click to show full abstract
We define a non-parametric estimator of the leverage effect by means of the covariance between the asset return and its volatility. The data are assumed to follow a stochastic volatility model driven by two continuous semi-martingales. The novelty of this paper is estimating the high frequency leverage effect using only a pre-estimation of the Fourier coefficients of the volatility. The Fourier methodology used in this work allows to obtain a consistent and asymptotically normaly distributed estimator without any manipulation of the data set in the time domain. The finite sample properties of the estimator are investigated in a simulation study.
Journal Title: Stochastic Processes and their Applications
Year Published: 2019
Link to full text (if available)
Share on Social Media: Sign Up to like & get
recommendations!