Home > Department of Statistics > Events > abstracts > Adaptive volatility estimation by local change point analysis

 

Adaptive volatility estimation by local change point analysis

When 2.00pm on Friday 3rd March
Where B617, Leverhulme Library, Columbia House
Presentations  
Speaker Volodia Spokoiny
From Weierstrass Institute
Abstract The talk considers the problem of modelling and estimation of the volatility of financial time series from historical data. First we consider parametric modelling with the special focus on the GARCH (1,1) specification. Some benefits and pitfalls of the parametric modelling are discussed. Next we consider a time varying parametric models and discuss the estimation procedure based on the local change point (LCP) analysis. Some important theoretical properties of the new method are presented. The performance of the proposed LCP procedure is compared with the GARCH-based methods in context of VaR analysis for real data.
For further information Thomas Hewlett (Postgraduate Administrator) Ext. 6879
Department of Statistics, Columbia House
Share:Facebook|Twitter|LinkedIn|