BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//talks.cam.ac.uk//v3//EN
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:Isaac Newton Institute Seminar Series
SUMMARY:Optimal experimental design for stochastic populat
ion models - Pagendam\, D (CSIRO Mathematics\, Inf
ormatics and Statistics)
DTSTART;TZID=Europe/London:20110718T170000
DTEND;TZID=Europe/London:20110718T173000
UID:TALK32072AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/32072
DESCRIPTION:Markov population processes are popular models for
studying a wide range of phenomena including the
spread of disease\, the evolution of chemical reac
tions and the movements of organisms in population
networks (metapopulations). Our ability to use th
ese models can effectively be limited by our knowl
edge about parameters\, such as disease transmissi
on and recovery rates in an epidemic. Recently\, t
here has been interest in devising optimal experim
ental designs for stochastic models\, so that prac
titioners can collect data in a manner that maximi
ses the precision of maximum likelihood estimates
of the parameters for these models. I will discuss
some recent work on optimal design for a variety
of population models\, beginning with some simple
one-parameter models where the optimal design can
be obtained analytically and moving on to more com
plicated multi-parameter models in epidemiology th
at involve latent states and non-exponentially dis
tributed infectious periods. For these more comple
x models\, the optimal design must be arrived at u
sing computational methods and we rely on a Gaussi
an diffusion approximation to obtain analytical ex
pressions for the Fisher information matrix\, whic
h is at the heart of most optimality criteria in e
xperimental design. I will outline a simple cross-
entropy algorithm that can be used for obtaining o
ptimal designs for these models. We will also expl
ore some recent work on optimal designs for popula
tion networks with the aim of estimating migration
parameters\, with application to avian metapopula
tions.\n
LOCATION:Seminar Room 1\, Newton Institute
CONTACT:Mustapha Amrani
END:VEVENT
END:VCALENDAR