Abstract
The volatility is a measure for the uncertainty of an asset’s return and is used to reflect the risk level of a financial asset. In this article, we consider the double kernel nonparametric estimator for the volatility function in a diffusion model over a finite-time span based on high frequency sampling data. Under the minimum conditions, the asymptotic mixed normality for the underlying estimator is derived. Moreover, the better finite-sample performance as variance reduction and even mean squared error reduction of the proposed estimator is verified through a Monte Carlo simulation study and an empirical analysis on overnight Shibor in China.
MSC 2010: Primary:
Data availability statement
The dataset for the empirical analysis is available as a supplementary file, which can also be derived from the following resource available in the public domain: http://www.shibor.org/shibor/web/DataService.jsp.