Best linear forecast of volatility in financial time series
Statistical Mechanics
2009-11-10 v1 Statistical Finance
Abstract
The autocorrelation function of volatility in financial time series is fitted well by a superposition of several exponents. Such a case admits an explicit analytical solution of the problem of constructing the best linear forecast of a stationary stochastic process. We describe and apply the proposed analytical method for forecasting volatility. The leverage effect and volatility clustering are taken into account. Parameters of the predictor function are determined numerically for the Dow Jones 30 Industrial Average. Connection of the proposed method to the popular ARCH models is discussed.
Keywords
Cite
@article{arxiv.cond-mat/0401360,
title = {Best linear forecast of volatility in financial time series},
author = {M. I. Krivoruchenko},
journal= {arXiv preprint arXiv:cond-mat/0401360},
year = {2009}
}
Comments
8 pages, REVTeX, one Postscript figure. Maple source code for calculation of the predictor function is attached in a separate .txt file