BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Modelling Pollock egg counts from the western Gulf of Alaska by a 
 zero-inflated Bayesian hierarchical space-time model - Geir Storvik\, Univ
 ersity of Oslo\, Norway.
DTSTART:20071127T123000Z
DTEND:20071127T133000Z
UID:TALK9188@talks.cam.ac.uk
CONTACT:Dr. Leah R Johnson
DESCRIPTION:Data from egg sampling surveys often contain a mixture of zero
  observations and large count or density values\, often with a high propor
 tion of zeros. We will consider a particular dataset giving walleye Polloc
 k egg counts from the western Gulf of Alaska\, from Kodiak Island to Unima
 h Pass\, in the years 1978-2000. The main interest will be to predict the 
 intensity of eggs as a process varying in space and time (both within and 
 between years). In this talk I will discuss a Bayesian approach for the an
 alysis of such data. The excessive number of zeros in the data is taken in
 to account by the use of a two stage modelling approach\, resulting in a z
 ero-inflated hierarchical space-time model. An underlying intensity proces
 s is assumed to both influence the probabilities of zeros and the amount o
 f eggs in non-zero observations. Dependence of covariates and spatio-tempo
 ral correlations are taken into account through the modelling of the under
 lying intensity process. Fitting is performed through Markov Chain Monte C
 arlo simulations. Results for the walley Pollock egg counts will be presen
 ted.\n\nThis talk will be based on joint work with Ingunn Tvete and Bent N
 atvig at the University of Oslo and Lorenzo Ciannelli at Oregon State Univ
 ersity.
LOCATION:Center for Mathematical Sciences\, room EL.09
END:VEVENT
END:VCALENDAR