The R-package 'surveillance' is a framework for the development of statistical methods for the modeling and change-point detection in time series of counts, proportions and categorical data as well as continuous-time epidemic like point process phenomena.
cdc- Stroup et al. (1989)
farrington- Farrington et al. (1996)
farringtonFlexible- Improved Farrington algorithm of Noufaily et al. (2012)
rki- The system previously used at the Robert Koch Institute, Germany
bayes- A Bayesian predictive posterior approach, see Höhle (2007)
boda- Bayesian outbreak detection algorithm based on a Generalized Additive Model fitted with INLA, see Manitz and Höhle (2013)
hmm- A predictive version of the Hidden Markov Model approach by Le Strat and Carrat (1999)
rogerson- Surveillance for time varying Poisson means as documented in Rogerson and Yamada (2004).
cusum- An approximate CUSUM method for time varying Poisson means as documented in Rossi et al (1999)
glrnb- Likelihood and generalized likelihood ratio detectors for time varying Poisson and negative binomial distributed series documented in Höhle and Paul (2008).
outbreakP- Semiparametric surveillance of outbreaks by Frisén and Andersson (2009)
categoricalCUSUM- includes change-point detection based on regression models for binomial and beta-binomial distributed response. Furthermore, multi-categorical models includes the multinomial logistic model, proportional odds model and the Bradley-Terry models, see Höhle (2010).
pairedbinCUSUM- paired-binary approach taken in Steiner et al. (1999)
stcd- (experimental) Point process based approach by Assuncao & Correa (2009)
surveillance. The paper describes three regression-oriented model frameworks capturing endemic and epidemic dynamics, which are illustrated by applications to infectious disease surveillance data:
twinstimfor geo-referenced event data (i.e., a spatio-temporal point pattern)
twinSIRfor the SI[R][S] event history of a fixed population
hhh4for multivariate time series of counts
algo.hhh- Held et al. (2005) and Paul et al. (2008)
algo.twins- Held et al. (2006)
hhh4- Paul and Held (2011)
twinSIR- continuous-time/discrete-space modelling as described in Höhle (2009). The
"epidata"class provides the associated data structure.
twinstim- continuous-time/continuous-space modelling as described in Meyer et al. (2012). The
"epidataCS"class holds the data, which mainly consist of the observed events and exogenous covariates on a space-time grid.
hhh4()(count data) and
twinstim()(individual-level data) frameworks with a view to modelling power-law decay of spatial interaction.
backprojNP- Non-parametric back-projection method of Becker et al. (1991) used in, e.g., Werber et al. (2013).
nowcast- Nowcasting using frequentist approaches described in Lawless (1994) as well as more flexible hierarchical Bayes approaches developed in Höhle and an der Heiden (2014).
The surveillance package is available for download from CRAN.
Current package development, help-forum and bugtracking is hosted through R-Forge:
From this page, snapshots of the current development version are available for download as a source tarball and a Windows binary.
You can easily install the current snapshot in R via
Currently, R-Forge does not offer binaries for MacOS X, but installation might succeed with the additional argument type="source" in the above call.
- Two recent manuscripts provide an overview as well as step-by-step instructions on what you can do with the package: Salmon et al. (2014) covers prospective monitoring whereas Meyer et al. (2014) covers spatio-temporal modelling.
- A good (but slightly outdated) introduction to the outbreak detection part of the package is provided in the paper surveillance: An R package for the surveillance of infectious diseases, Computational Statistics (2007), 22(4), pp. 571-582. [preprint]
- A more recent description can be found in the book chapter Aberration detection in R illustrated by Danish mortality monitoring (2010), M. Höhle and A. Mazick, To appear in T. Kass-Hout and X. Zhang (Eds.) Biosurveillance: A Health Protection Priority, CRC Press. [preprint]. Note: As ISO 8601 handling is not fully implemented in R on Windows the demo("biosurvbook") will only run with package version >= 1.2, where a workaround was implemented.
- An overview of statistical methods and implementational usage is given the course notes of several courses on the package, e.g. the course notes of the lecture Temporal and spatio-temporal modelling of infectious diseases at the Department of Statistics, University of Munich, Oct 10-13, 2011 or the shortcourse Statistical surveillance of infectious diseases held at the Department of Statistics, Universidade Federal de Minas Gerais (UFMG), Belo Horizonte, Brazil, Nov 27-28, 2008.
- Invited talk held at the 2008 ESCAIDE satellite workshop on
Computer supported outbreak detection and signal management(R-File, Data from SurvStat@RKI)
- Application of the package in veterinary public health surveillance is described in Statistical approaches to the surveillance of infectious diseases for veterinary public health [preprint].
- Read the package vignettes or look here for further preprints.
- Sometimes pictures says more than 1000 words:
- Michael Höhle, Department of Mathematics, Stockholm University, Sweden (Project Admin)
- Sebastian Meyer, Epidemiology, Biostatistics and Prevention Institute (EBPI), University of Zurich, Switzerland
- Michaela Paul (previously: University of Zurich, Switzerland)
- Maëlle Salmon, Department for Infectious Disease Epidemiology, Robert Koch Institute, Germany
- Former student programmers: C. Lang, A. Riebler, V. Wimmer
- Contributions by: L. Held, T. Correa, M. Hofmann, J. Manitz, D. Sabanés Bové, D. Schumacher, S. Steiner, M. Virtanen
- German Science Foundation (DFG, 2003-2006)
- Munich Center of Health Sciences (MC-Health, 2007-2010)
- Swiss National Science Foundation (SNSF, 2007-2010, projects #116776 and #124429)
- Swiss National Science Foundation (SNSF, 2012-2015, project #137919)
- Robert Koch Institute, Berlin, Germany (2012-2015, Ph.D. project 'Modern surveillance algorithms for public health monitoring')