BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Modelling multivariate nonstationarity - Olhede\, S (University Co
 llege London)
DTSTART:20140115T113000Z
DTEND:20140115T121500Z
UID:TALK49926@talks.cam.ac.uk
CONTACT:Mustapha Amrani
DESCRIPTION:Co-authors: Adam Sykulski (UCL)\, Jonathan Lilly (NWRA)\, Jeff
 rey Early (NWRA) \n\nNonstationarity\, like all non-properties\, is hard t
 o pin down precisely\, and to model sufficiently flexibly for realism\, bu
 t at the same time model in a sufficiently constrained fashion to allow fo
 r good inference. Modelling is inevitably time or frequency domain\, where
  the two branches of thinking are traditionally linked via the local spect
 rum\, or another bilinear representation of the data.\n \nThe resolution i
 n the representation is constrained by the choice of representation. There
  are of course many alternatives to modelling the local Fourier transform\
 , but these have been mainly parametric or have been developed for a speci
 fic application.\n\nA problem in general is chosing a representation that 
 suits analysis of more than one series. We shall focus on how our notion o
 f nonstationarity must change when thinking of such observations\, focussi
 ng on what features are present in bivariate series\, that cannot be found
  in univariate observations.\n
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR