tnet (version 2.6)

small_world_test_tm: Finds the observed and randomly expected clustering coefficient and average shortest distance

Description

Finds the observed and randomly expected values of the global clustering coefficient and average shortest (geodesic) distance in two-mode networks. A network is considered to be a small world if the observed values are comparable to the random ones. The summary information is printed to the screen, and the underlying information is returned as a list. Based on this list, significance can be calculated (e.g., whether the observed values are within the 95

Usage

small_world_test_tm(net, NR=1000, step=c(1,2))

Arguments

net

A weighted edgelist

NR

Number of random networks

step

Which steps to perform: 1) calculating values on observed network, and 2) calculating values on link reshuffled networks.

Value

• Summary information is written to the screen, and detailed information is returned as follows: [[1]] This is variable 1, which is the clustering coefficient: clustering_tm(net) [[2]] This is variable 2, which is binary distance matrix: distance_w(projecting_tm(net, "binary")) [[3]] This is variable 3, which is matrix with the results from the weight reshuffled random networks (rows) and different measures (columns), which are 1: clustering_tm(net.r) 2: average binary distance 3: size of giant component

Examples

## Load sample data
sample <- cbind(
i=c(1,1,2,2,2,3,3,4,5,5,6),
p=c(1,2,1,3,4,2,3,4,3,5,5))

## Run the programme
small_world_test_tm(sample, NR=2)