BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Optimal design and properties of correlated processes with semicon
 tinuous covariance - Stehlk\, M (Johannes Kepler Universitt)
DTSTART:20110721T143000Z
DTEND:20110721T151500Z
UID:TALK32117@talks.cam.ac.uk
CONTACT:Mustapha Amrani
DESCRIPTION:Semicontinuous covariance functions have been used in regressi
 on and kriging by many authors. In a recent work we introduced purely topo
 logically defined regularity conditions on covariance kernels which are st
 ill applicable for increasing and infill domain asymptotics for regression
  problems and kriging. These conditions are related to the semicontinuous 
 maps of Ornstein Uhlenbeck Processes. Thus these conditions can be of bene
 fit for stochastic processes on more general spaces than the metric ones. 
 Besides\, the new regularity conditions relax the continuity of covariance
  function by consideration of a semicontinuous covariance. We discuss the 
 applicability of the introduced  topological regularity conditions for opt
 imal design of random fields. A stochastic process with parametrized mean 
 and covariance is observed over a compact set. The information obtained fr
 om observations is measured through the information functional (defined on
  the Fisher information matrix). We start with discussion on the role of e
 quidistant designs for the correlated process. Various aspects of their pr
 ospective optimality will be reviewed and some issues on designing for spa
 tial processes will be also provided. Finally we will concentrate on relax
 ing the continuity of covariance. We will introduce the regularity conditi
 ons for isotropic processes with semicontinuous covariance such that incre
 asing domain asymptotics is still feasible\, however more flexible behavio
 r may occur here. In particular\, the role of the nugget effect will be il
 lustrated and practical application of stochastic processes with semiconti
 nuous covariance will be given. \n
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR