Dear all,

The Edinburgh local group of the Royal Statistical Society will be hosting
the following event on Thursday 19th September. The event is free, and
open to all; no registration is required.

===============================================
Thursday 19th September 2013
Professor Andrew B Lawson and Dr Janine B Illian
Bayesian computing with INLA
ICMS, 15 South College Street, Edinburgh EH8 9AA
Meeting starts 6pm, tea and coffee from 5.30pm

===============================================
Professor Andrew B Lawson (Department of Public Health Sciences, Medical
University of South Carolina)

Bayesian Disease Mapping with INLA: an overview

Abstract:

Bayesian Disease Mapping often focusses on the hierarchical modeling of
health outcomes in predefined small areas (e.g. postcodes, counties). The
data level outcome is usually a count of disease and a risk parameter
(relative risk) is to be estimated in small areas.  A hierarchical model
can be derived that includes a parsimonious description of the risk
variation. When spatio-temporal (ST) variation is considered a variety of
models can be conceived. In particular, separable effects are often
assumed, with the addition of a ST interaction. The integrated nested
Laplace Approximation has recently been efficiently implemented in R for a
range of likelihoods and associated prior distributions (Rue et al, 2009).
The package INLA can be used to fit a range of spatial and ST models to
small area data. In this talk I will present a number of examples of the
possible analyses for the famous Ohio county level respiratory cancer data
set and, if time permits, parish level FMD data from the 2001 Cumbrian
outbreak. Some example INLA code for spatial and ST models can be found in
Appendix D of Lawson (2013) as well as the INLA website
(http://www.r-inla.org/).

References:

Rue, H., Martino, S., and Chopin, N. (2009) Approximate Bayesian
inferences for latent Gaussian models by using integrated nested Laplace
approximations. JRSS B, 71, 319-392

Lawson, A. B. (2013) Bayesian Disease Mapping: Hierarchical Modeling in
Spatial Epidemiology. CRC Press 2nd Ed.


===============================================
Dr. Janine B Illian (University of St. Andrews)
Fitting Complex Spatial Models in INLA: developments and extensions

Abstract:

Integrated nested Laplace approximation (INLA) may be used to fit a large
class of (complex) statistical models. While MCMC methods use stochastic
simulations for estimation, integrated nested Laplace approximation (INLA)
is based on deterministic approximations where there are no convergence
issues. INLA is a very accurate and computationally superior alternative
to MCMC and may be used to fit a large class of
models, latent Gaussian models.

Since INLA is fast, complex modelling has become greatly facilitated and
has also become more accessible to non-specialists. In addition, due to
the fact that the fitting approach is embedded in a large and general
class of statistical models, very general types of models may be
considered. This allows us a lot more flexibility in the choice of model
than previously and hence the models to capture interesting aspects of the
data and consequently the system they are relevant for. In the context of
spatial statistics, for example, we can now fit models to spatial point
patterns of high dimensionality, replicated point patterns, hierarchically
marked point patterns etc. In many cases, analysing these data sets with
MCMC approaches would be very cumbersome and computationally prohibitive.

The INLA-methodology has been implemented in C, and the associated
numerical calculations and algorithms rely on an efficient implementation
of numerical procedures for Gaussian Markov random fields (GMRF), in
particular the algorithms in the C-library GMRFLib. However, most users do
not need to worry about this, as the INLA-methodology has been made
accessible through a user-friendly R-library, R-INLA, described and
available for download at www.r-inla.org. Specifying and fitting models
using R-INLA is just as easy as applying standard routines in R, for
example fitting generalised linear models, and it also provides great
flexibility with regard to the models that may be fitted. In order to
illustrate INLA's versatility I will discuss a range of spatial and
non-spatial examples and present a number of recent developments. This
concerns generalisations of the methodology as well as new functionality
within the R-INLA library.
===============================================

Many thanks,

Adam Butler ([log in to unmask])
Edinburgh local group of the Royal Statistical Society
http://www.rss.org.uk/edinburgh











-- 
Biomathematics and Statistics Scotland (BioSS) is formally part of The
James Hutton Institute (JHI), a registered Scottish charity No. SC041796
and a company limited by guarantee No. SC374831

You may leave the list at any time by sending the command

SIGNOFF allstat

to [log in to unmask], leaving the subject line blank.