An Examination of the Continuous-Time Dynamics of International Volatility Indices Amid the Recent Market Turmoil
44 Pages Posted: 27 Apr 2013
Date Written: November 11, 2009
Abstract
Volatility indices have been designed for many markets as gauges to measure investors' fear of market crash. The recent market turmoil has produced historically high volatility levels, in some cases around four times higher than their previous average levels. We take a look at the behavior of various volatility indices by including the recent market turmoil into the data. We estimate various continuous-time models for different volatility indices with focus on the structure of the drift and diffusion functions. Two methodologies are utilized: the maximum likelihood estimation, and Ait-Sahalia's parametric specification test. While the results from the parametric specification test advocate strongly for specifying more flexible drift and diffusion functions, nonlinear drift structure often only adds negligible benefit in terms of the likelihood function value. Our results call for caution against finite sample bias when adopting a particular model or fixing a particular parameter vector.
Keywords: Volatility Indices, Continuous-time Dynamics, Maximum Likelihood Estimation, Parametric Specification Test
JEL Classification: C60, G12, G13
Suggested Citation: Suggested Citation
Do you have negative results from your research you’d like to share?
Recommended Papers
-
Nonparametric Pricing of Interest Rate Derivative Securities
-
Back to the Future: Generating Moment Implications for Continuous-Time Markov Processes
-
Maximum-Likelihood Estimation of Discretely Sampled Diffusions: A Closed-Form Approach
-
Maximum Likelihood Estimation of Discretely Sampled Diffusions: A Closed-Form Approach
-
Is the Short Rate Drift Actually Nonlinear?
By David A. Chapman and Neil D. Pearson
-
Nonparametric Density Estimation and Tests of Continuous Time Interest Rate Models
-
Maximum Likelihood Estimation of Generalized Ito Processes with Discretely Sampled Data
By Andrew W. Lo
-
Maximum Likelihood Estimation of Generalized Ito Processes with Discretely Sampled Data
By Andrew W. Lo
-
Closed-Form Likelihood Expansions for Multivariate Diffusions