Dear R Community,
I would like to announce the package "surveillance", which provides
methods for the surveillance of count data time series originating
from the routine collection of public health data.
The package addresses epidemiologists and statisticians working with
routine surveillance, but it also offers an infrastructure for
developers of new detection algorithms.
Implemented outbreak detection algorithms are:
* Stroup et al. (1989)
* Farrington et al. (1996)
* A Bayesian predictive posterior approach
* Time varying Poisson means as documented in Rogerson and Yamada (2004)
* Approximate CUSUM method for time varying Poisson means by
Rossi et al. (1999)
* A generalized likelihood ratio detector for time varying Poisson
and and negative binomial means
Modelling routines:
* A Poisson and negative binomial model for the analysis of
multivariate infectious disease surveillance data described in Held
et al. (2005)
The paper available from http://dx.doi.org/10.1007/s00180-007-0074-8
provides a good overview of the package. Source code and binaries
(currently version 0.9-8) are available from CRAN. Visit the R-Forge
project web page for more information, development versions and forums
to discuss ideas and report bugs:
http://surveillance.r-forge.r-project.org/
I would appreciate hearing about your experiences with the package.
Best regards,
Michael
-on behalf of the surveillance development team
--
Michael H?hle, Ph.D.
Department of Statistics
University of Munich
Ludwigstr. 33
80539 Munich
Germany
Homepage: http://www.stat.uni-muenchen.de/~hoehle
_______________________________________________
R-packages mailing list
R-packages at r-project.org
https://stat.ethz.ch/mailman/listinfo/r-packages
