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 design of blocked and split-plot experimen
ts for fixed-effects and variance-components estim
ation - Goos\, P (Antwerpen)
DTSTART;TZID=Europe/London:20110831T090000
DTEND;TZID=Europe/London:20110831T093000
UID:TALK32587AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/32587
DESCRIPTION:Many industrial experiments\, such as block experi
ments and split-plot experiments\, involve one or
more restrictions on the randomization. In these e
xperiments the observations are obtained in groups
. A key difference between blocked and split-plot
experiments is that there are two sorts of factors
in split-plot experiments. Some factors are held
constant for all the observations within a group o
r whole plot\, whereas others are reset independen
tly for each individual observation. The former fa
ctors are called whole-plot factors\, whereas the
latter are referred to as sub-plot factors. Often\
, the levels of the whole-plot factors are\, in so
me sense\, hard to change\, while the levels of th
e sub-plot factors are easy to change. D-optimal d
esigns\, which guarantee efficient estimation of t
he fixed effects of the statistical model that is
appropriate given the random block or split-plot s
tructure\, have been constructed in the literature
by various authors. However\, in general\, model
estimation for block and split-plot designs requir
es the use of generalized least squares and the es
timation of two variance components. We propose a
new Bayesian optimal design criterion which does n
ot just focus on fixed-effects estimation but also
on variance-component estimation. A novel feature
of the criterion is that it incorporates prior in
formation about the variance components through lo
g-normal or beta prior distributions. Finally\, we
also present an algorithm for generating efficien
t designs based on the new criterion. We implement
several lesser-known quadrature approaches for th
e numerical approximation of the new optimal desig
n criterion. We demonstrate the practical usefulne
ss of our work by generating optimal designs for s
everal real-life experimental scenarios.\n\n\n
LOCATION:Seminar Room 1\, Newton Institute
CONTACT:Mustapha Amrani
END:VEVENT
END:VCALENDAR