network.permutation: Permutation Test for Network Measures

In AlexChristensen/NetworkToolbox: Methods and Measures for Brain, Cognitive, and Psychometric Network Analysis

Permutation Test for Network Measures

Description

Computes a permutation test to determine whether there are difference in centrality and global network measures

Usage

network.permutation(
  sample1 = NULL,
  sample2 = NULL,
  iter,
  network = c("glasso", "ising", "TMFG", "LoGo"),
  measure = c("betweenness", "closeness", "strength", "eigenvector", "rspbc", "hybrid",
    "ASPL", "CC", "S", "Q"),
  alternative = c("less", "greater", "two.tailed"),
  ncores,
  prev.perm = NULL,
  ...
)

Arguments

sample1	Matrix or data frame. Sample to be compared with sample2
sample2	Matrix or data frame. Sample to be compared with sample1
iter	Numeric. Number of iterations to perform. Defaults to 1000
network	Character. Network estimation method to apply to the datasets. Defaults to "glasso"
measure	Character. Network measure to be compared in the permutation test
alternative	Character. Alternative hypothesis test to perform. Defaults to "two.tailed"
ncores	Numeric. Number of computer processing cores to use for bootstrapping samples. Defaults to n - 1 total number of cores. Set to any number between 1 and maximum amount of cores on your computer (see parellel::detectCores())
prev.perm	network.permutation class object. An object of previously performed permutation test. The networks generated in the previous permutation will be used to compute other network measures. This saves time when computing multiple permutation tests
...	Additional arguments for EBICglasso

Value

Returns a list containing two objects:

result

The results of the permutation test. For centrality measures, this is a matrix where the rows represent each node and the columns are the observed values of the centrality measure for sample1, sample2, and the p-value from the permutation test. For global network measures, this is a vector with the observed values of the global network measure for sample1, sample2, and the p-value from the permutation test.

networks

A list containing two lists: network1 and network2. The network lists correspond to the networks generated in the permutation test for sample1 and sample2, respectively. This output is used primarily for the computation of other network measures using the same datasets (see prev.perm explanation)

Author(s)

Alexander Christensen <[e-mail]>

Examples

# Split data (only for example)
split1 <- neoOpen[c(1:401),]
split2 <- neoOpen[c(402:802),]


# Perform permutation test
perm.str <- network.permutation(split1, split2, iter = 1000, network = "glasso",
measure = "strength", alternative = "two.tailed", ncores = 2)

# Check results
perm.str$result

# Permutation to check other measures (using networks from previous result)
perm.aspl <- network.permutation(prev.perm = perm.str, measure = "ASPL", ncores = 2)

# Check results
perm.aspl$result

AlexChristensen/NetworkToolbox documentation built on March 6, 2023, 5:08 p.m.