held at the Department of Statistics, Universidade Federal de Minas
Gerais (UFMG), Belo Horizonte, Brazil, Nov 27-28, 2008.
Course contents
Public health authorities have, in an attempt to meet the threats of
infectious diseases, created comprehensive mechanisms for the
collection of disease data. The vast amounts of data resulting from
this acquisition demands the development of algorithms for the
automated detection of abnormalities and changes.
This short course covers statistical aspects of how to treat such data
when - possibly after some preprocessing - one has univariate
or multivariate time series of case counts. Two aspects are covered:
retrospective modelling of surveillance time series and prospective
surveillance, where the aim is to quickly determine the onset of health
relevant events. Statistical methods and algorithms dealing with such
temporal surveillance are introduced and their use is illustrated
through the R package 'surveillance'.
The structure of the short course will be as follows:
Motivating examples: Why is there an interest in the automatic
monitoring of routine collected public health data.
Overview of temporal surveillance and introduction to the R
package 'surveillance'
Specific treatment of Shewhart methods and CUSUM based methods.
Among others this includes: The historical limits method, the
Farrington et al. (1996) procedure, Rossi et al. (1999), Rogerson &
Yamada (2004) and Höhle & Paul (2008).
Comparing surveillance methods: empirical investigations and
theoretical considerations
Towards multivariate surveillance - how to extend the known
approaches?
Outlook - spatio-temporal epidemic modelling
The intended audience of the course are biostatisticians,
epidemiologists and master students of these directions. Prerequisites
are a knowledge of statistics up to a basic understanding of Poisson
regression models and familiarity with R - a free software environment
for statistical computing and graphics.
Speaker: Michael
Höhle, Department of Statistics, Ludwig-Maximilians-Universität
München, Germany
Practical information
Location:
Seminar Room 2076, Instituto de
Ciências Exatas, UFMG
Dates:
Thursday 27 Nov 2008, from 11:10 to
12:30
Friday 28 Nov 2008: from 11:10 to 12:30 and 13:30 to 15:00
