|
Activity Number:
|
402
- Variance, Change Points, and Outliers
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 1, 2017 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Business and Economic Statistics Section
|
|
Abstract #323610
|
|
|
Title:
|
Multivariate Stochastic Volatility Modeling via the Spectral Decomposition
|
|
Author(s):
|
Victor Solo*
|
|
Companies:
|
University of New South Wales
|
|
Keywords:
|
Stochastic Volatility ;
Lie Group ;
Asset Pricing
|
|
Abstract:
|
A lot of recent effort has gone into multivariate stochastic volatility modeling because of its compelling applications in asset pricing. Current approaches include multivariate GARCH, Cholesky decomposition and the Wishart process method. However these methods do not directly model the eigenvalues which carry interpretable information about the evolution of volatility. After reviewing related work, we sketch, in a simple case, the beginnings of a new approach based on spectral decomposition of the covariance matrix. The matrix of eigenvectors evolves as a Brownian motion in a Lie group and a scalar stochastic volatility model is posited for eigenvalues. We illustrate with a simple example.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2017 program
|
