---------------------------- REMINDER
-------------------------------------
ROYAL STATISTICAL SOCIETY
JOINT MEETING of COMPUTING SECTION, SHEFFIELD LOCAL GROUP and
GENERAL APPLICATIONS SECTION
Wednesday 15th March 2006, 2:00pm - 4:30pm at Sheffield University (Tea
3:25pm)
Lecture room 7, Hicks Building (1st floor/floor E), Hounsfield Road, S3
7RH
COMPUTERISED SPATIAL STATISTICS
-------------------------------------------------------------------------------
Speakers and abstracts
(1) Spatio-temporal modelling of zooplankton in the North Atlantic
S.N. WOOD, W. HORBELT, D.C. SPEIRS, M.R. HEATH and W.S.C. GURNEY
(University of Bath)
Calanus finmarchicus is the dominant zooplankton species over much of the
North Atlantic. It has an unusual life-cycle involving overwintering in
very deep waters at very cold temperatures and then re-ascending to breed
in the spring. Because of the considerable distances that individual
calanus are transported during their lives, calanus population dynamics
can only be properly understood at the scale of the whole North Atlantic.
This involves the formulation of physically driven spatially explicit
population dynamic models describing the whole North Atlantic population.
However, given the complexity of the calanus life-cycle, key model
parameters can only be estimated by treating this complex model as a
statistical model and fitting it to data on calanus abundance. This talk
describes an approach to doing this, involving a (parallelized) hybrid of
finite differencing and autodifferentiation to obtain derivatives of the
model predictions w.r.t. the parameters, coupled with a modified
Gauss-Newton fitting method.
(2) Computational methods in spatial epidemiology
V. GOMEZ-RUBIO and N. BEST
(Dept. of Epidemiology and Public Health, Imperial College London)
The talk will describe some of the state-of-the-art models employed in
spatial statistics and, specifically, in spatial epidemiology. A brief
introduction on how WinBugs can be used to fit spatial models and
associated computational challenges will be given. This will be followed
by a description of how GeoBugs can help with the definition of the
spatial models and with the display of results in a map. Finally, we will
show how WinBugs can be linked to the R statistical language for initial
data management or representation and exploitation of WinBUGS results by
R’s enhanced plotting capabilities. This part will include descriptions of
recent packages developed by the R user community.
(3) Adaptive sampling for automated soil mapping
B. MARCHANT
(Rothamsted Research, Harpenden)
A major problem for management of within-field variation is obtaining
adequate information on the variations of important variables at
acceptable cost. If soil properties are to be mapped with adequate
precision, then the sampling intensity needed will differ between fields.
Therefore farmers and agronomists run the risk of completing a survey then
finding that they have substantially over-sampled and so wasted effort, or
that they are not able to produce a reasonable map from the data because
they are too sparse. In this talk we describe the development of adaptive
methods for designing sample schemes which are suited to the property
being measured when we start with little or no information on the spatial
variability of the variable.
All welcome.
Further information from Nick Fieller (email [log in to unmask],
tel. 0114 222 3831).
---------------------------------------------------------------------
Sabine Landau
Dept of Biostatistics & Computing, PO Box 20
Institute of Psychiatry, KCL
De Crespigny Park
London SE5 8AF, UK
|