Title: Estimation of the volatility in SV models using singular spectrum analysis
Authors: Javier Garcia - University of the Basque Country (Spain)
Josu Arteche - University of the Basque Country UPV/EHU (Spain) [presenting]
Abstract: One of the main difficulties that Stochastic Volatility models have to face when applied to financial time series is estimating the in-sample volatility. To solve this problem,a non-parametric strategy based on Singular Spectrum Analysis is proposed. Its main advantage is its generality because it does not impose any parametric restriction on the volatility component: only some spectral structure is needed to identify it separately from noisy components. Its convincing performance is shown in an extensive MonteCarlo analysis that includes stationary and nonstationary long memory, short memory and level shifts in the volatility component, which are models often used for financial time series. Its applicability is finally illustrated in a daily Dow Jones Industrial index series and an intraday series from the Spanish Ibex35 stock index.