The R Journal: article published in 2019, volume 11:2

The IDSpatialStats R Package: Quantifying Spatial Dependence of Infectious Disease Spread PDF download
John R. Giles, Henrik Salje and Justin Lessler , The R Journal (2019) 11:2, pages 308-327.

Abstract Spatial statistics for infectious diseases are important because the spatial and temporal scale over which transmission operates determine the dynamics of disease spread. Many methods for quantifying the distribution and clustering of spatial point patterns have been developed (e.g. K function and pair correlation function) and are routinely applied to infectious disease case occurrence data. However, these methods do not explicitly account for overlapping chains of transmission and require knowledge of the underlying population distribution, which can be limiting when analyzing epidemic case occurrence data. Therefore, we developed two novel spatial statistics that account for these effects to estimate: 1) the mean of the spatial transmission kernel, and 2) the τ-statistic, a measure of global clustering based on pathogen subtype. We briefly introduce these statistics and show how to implement them using the IDSpatialStats R package.

Received: 2019-01-02; online 2019-12-26, supplementary material, (3 Kb)
CRAN packages: lgcp, ppmlasso, spdep, ads, spatstat, splancs, IDSpatialStats, DCluster, SGCS, sparr
CRAN Task Views cited directly: Spatial
CRAN Task Views implied by cited CRAN packages: Spatial, SpatioTemporal, Survival

CC BY 4.0
This article and supplementary materials are licensed under a Creative Commons Attribution 4.0 International license.

  author = {John R. Giles and Henrik Salje and Justin Lessler},
  title = {{The IDSpatialStats R Package: Quantifying Spatial Dependence
          of Infectious Disease Spread}},
  year = {2019},
  journal = {{The R Journal}},
  doi = {10.32614/RJ-2019-043},
  url = {},
  pages = {308--327},
  volume = {11},
  number = {2}