Type: Package
Title: Flexible Scan Statistics
Version: 0.2.2
Author: Zhicheng Du, Yuantao Hao
Maintainer: Zhicheng Du <dgdzc@hotmail.com>
Depends: R (≥ 2.10)
Description: An easy way to conduct flexible scan. Monte-Carlo method is used to test the spatial clusters given the cases, population, and shapefile. A table with formal style and a map with clusters are included in the result report. The method can be referenced at: Toshiro Tango and Kunihiko Takahashi (2005) <doi:10.1186/1476-072X-4-11>.
License: GPL-3
Imports: smerc, sp, spdep, methods, graphics, spatialreg
Encoding: UTF-8
LazyData: true
NeedsCompilation: no
Packaged: 2022-01-06 07:16:39 UTC; dgdzc
Repository: CRAN
Date/Publication: 2022-01-06 07:40:02 UTC

Flexible Scan Statistics

Description

An easy way to conduct flexible scan. Monte-Carlo method is used to test the spatial clusters given the cases, population, and shapefile. A table with formal style and a map with clusters are included in the result report. The method can be referenced at: Toshiro Tango and Kunihiko Takahashi (2005) <doi:10.1186/1476-072X-4-11>.

Usage

flexscan(map,case,pop,nsim,k,alpha,isplot,col)

Arguments

map

spatial object, typically a shapefile read in using 'rgdal::readOGR'

case

numeric, a vector of number of cases for each region of 'map'; it is noteworthy that the order of regions in 'case' is corresponding to that in 'map'

pop

numeric, a vector of number of population for each region of 'map'; it is noteworthy that the order of regions in 'pop' is corresponding to that in 'map'

nsim

numeric, the number of simulations for Monte Carlo test; the default is 999

k

numeric, the maximum number of regions allowed for clusters; the default is 10

alpha

numeric, the significance level of flexible scan test; the default is 0.05

isplot

logical, wether to plot the results; the default is 0.05

col

color vector, two colors for most likely cluster and secondary cluster; the default is c("red","blue")

Value

data.frame

a data.frame containing 8 variables as follows:

Cluster Type

most likely cluster or secondary cluster

Region ID

region id for each cluster; it is noteworthy that the 'ID' is the order of regions in 'map'

Observed Cases

observed cases for each cluster

Expected Cases

expected cases for each cluster

SR

standardized ratio of observed to expected cases

RR

relative risk for each cluster

LLR

loglikelihood ratio for each cluster

P Value

p value of likelihood ratio test for each cluster

Note

Please feel free to contact us, if you have any advice and find any bug!

Reference:

Tango, T. & Takahashi, K. A Flexibly Shaped Spatial Scan Statistic for Detecting Clusters. INT J HEALTH GEOGR. 4, 11 (2005).

Updates:

Version 0.2.0: Fix the bugs according to the dependent package of "smerc" version 1.1

Version 0.2.2: Fix the bugs according to the dependent package of "spdep"

Author(s)

Zhicheng Du<dgdzc@hotmail.com>, Yuantao Hao<haoyt@mail.sysu.edu.cn>

Examples

  data(map)
  data(sample)
  # simple example for checks; turn the warnings back on using 'options(warn=0)'
  options(warn=-1)
  flexscan(map,case=sample$case,pop=sample$pop,k=3,isplot=FALSE,nsim=10)
## Not run: 
 flexscan(map,case=sample$case,pop=sample$pop)

## End(Not run)

Shapefile

Description

There 123 tiles in the map.

Usage

map

Sample Data

Description

There are two variables in the 'sample' including 'case' and 'pop'.

Usage

sample