node.redundant: Detects Redundant Nodes in a Network

Description Usage Arguments Value Author(s) References Examples

Description

Identifies redundant nodes in the network based on several measures. Computes the weighted topological overlap between each node and every other node in the network. The weighted topological overlap is implemented using the method from Nowick et al. (2009; see references) and the function wTO from the wTO package.

Usage

1
2
3
4
5
6
7
8
9
node.redundant(
  data,
  n = NULL,
  sig,
  method = c("wTO", "pcor", "cor"),
  thresh = TRUE,
  type = c("alpha", "adapt"),
  plot = FALSE
)

Arguments

data

Matrix or data frame. Input can either be data or a correlation matrix

n

Numeric. If input in data is a correlation matrix and method = "wTO", then sample size is required. Defaults to NULL

sig

Numeric. p-value for significance of overlap (defaults to .05)

method

Character. Computes weighted topological overlap ("wTO" using EBICglasso), partial correlations ("pcor"), and correlations ("cor"). Defaults to "wTO"

thresh

Boolean. Should a threshold be applied? Defaults to TRUE. If TRUE, then based on a certain threshold only redundancies above that value will be returned. Uses argument "sig" to input the desired threshold. Defaults for each method:

  • "wTO" .20

  • "pcor" .20

  • "cor" .70

type

Character. Type of significance. Computes significance using the standard p-value ("alpha"), or adaptive alpha p-value (adapt.a). Defaults to "adapt"

plot

Boolean. Should redundancies be plotted in a network plot? Defaults to FALSE

Value

Returns a list:

redundant

Vectors nested within the list corresponding to redundant nodes with the name of object in the list

data

Returns original data

weights

Returns weights determine by weighted topological overlap or partial correlations

network

The network compute by EBICglasso

descriptives
  • basicA vector containing the mean, standard deviation, median, median absolute deviation (MAD), 3 times the MAD, 6 times the MAD, minimum, maximum, and critical value for the overlap measure (i.e., weighted topological overlap, partial correlation, or threshold)

  • centralTendencyA matrix for all (aboslute) non-zero values and their respective standard deviation from the mean and median absolute deviation from the median

distribution

Distribution that was used to determine significance

Author(s)

Alexander Christensen <alexpaulchristensen@gmail.com>

References

# Simulation using node.redundant
Christensen, A. P. (2020). Towards a network psychometrics approach to assessment: Simulations for redundancy, dimensionality, and loadings (Unpublished doctoral dissertation). University of North Carolina at Greensboro, Greensboro, NC, USA. doi: 10.31234/osf.io/84kgd

# Implementation of node.redundant
Christensen, A. P., Golino, H., & Silvia, P. J. (in press). A psychometric network perspective on the validity and validation of personality trait questionnaires. European Journal of Personality. doi: 10.1002/per.2265

# wTO measure
Nowick, K., Gernat, T., Almaas, E., & Stubbs, L. (2009). Differences in human and chimpanzee gene expression patterns define an evolving network of transcription factors in brain. Proceedings of the National Academy of Sciences, 106, 22358-22363. doi: 10.1073/pnas.0911376106

Examples

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
# obtain SAPA items
items <- psychTools::spi[,c(11:20)]

# weighted topological overlap
redund <- node.redundant(items, method = "wTO", type = "adapt", plot = TRUE)

# partial correlation
redund <- node.redundant(items, method = "pcor", type = "adapt", plot = TRUE)

# threshold
redund <- node.redundant(items, method = "pcor", thresh = TRUE, sig = .20, plot = TRUE)

EGAnet documentation built on Feb. 17, 2021, 1:06 a.m.