BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Detection of multiple structural breaks in multivariate time serie
 s - Dette\, H (Ruhr-Universitt Bochum)
DTSTART:20140114T145000Z
DTEND:20140114T153000Z
UID:TALK49861@talks.cam.ac.uk
CONTACT:Mustapha Amrani
DESCRIPTION:We propose a new nonparametric procedure for the detection and
  estimation of multiple structural breaks in the autocovariance function o
 f a multivariate (second-order) piecewise stationary process\, which also 
 identifies the components of the series where the breaks occur. The new me
 thod is based on a comparison of the estimated spectral distribution on di
 fferent segments of the observed time series and consists of three steps: 
 it starts with a consistent test\, which allows to prove the existence of 
 structural breaks at a controlled type I error. Secondly\, it estimates se
 ts containing possible break points and finally these sets are reduced to 
 identify the relevant structural breaks and corresponding components which
  are responsible for the changes in the autocovariance structure. In contr
 ast to all other methods which have been proposed in the literature\, our 
 approach does not make any parametric assumptions\, is not especially desi
 gned for detecting one single change point and addresses the problem of mu
 ltiple structural breaks in the autocovariance function directly with no u
 se of the binary segmentation algorithm. We prove that the new procedure d
 etects all components and the corresponding locations where structural bre
 aks occur with probability converging to one as the sample size increases 
 and provide data-driven rules for the selection of all regularization para
 meters. The results are illustrated by analyzing financial returns\, and i
 n a simulation study it is demonstrated that the new procedure outperforms
  the currently available nonparametric methods for detecting breaks in the
  dependency structure of multivariate time series.\n
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR