powerlaw.stat: Discrete Power-Law Scan Statistic

In SNscan: Scan Statistics in Social Networks

Description

The discrete power-law scan statistic evaluates the statistic which compares the node attribute within the subgraph with that outside the subgraph while the node attribute follows the power-law distribution.

Usage

powerlaw.stat(obs, pop = 1, zloc, xmin = 1, zetatable = NULL)

Arguments

obs	Numeric vector of observation values.
pop	Numeric vector of population values; default = 1.
zloc	Numeric vector of selected nodes.
xmin	The minmum value of power law distribution; defaut = 1.
zetatable	When xmin=1, set up the data(zetatable).

Value

Three values will be returned. The first value is test statistic. The second is the estimated means which estimated outside the selected nodes. The third is estimated means which estimated within the selected nodes.

Author(s)

Taichi Wang <[e-mail]>

References

Wang, T. C., Phoa, F. K. H., & Hsu, T. C. (2015). Power-law distributions of attributes in community detection. Social Network Analysis and Mining, 5(1), 1-10.

See Also

rplcon,zetatable,conpowerlaw.stat

Examples

library(poweRlaw)
data(zetatable)
x=rpldis(n=100, xmin=1, alpha=1.5) #function from poweRlaw
powerlaw.stat(obs=x,zloc=1:5,zetatable = zetatable)

SNscan documentation built on May 2, 2019, 8:26 a.m.