LoGo: Local/Global Inversion Method

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

Description

Applies the Local/Global method to estimate a Gaussian Graphical Model (GGM) using a TMFG-filtered network (see and cite Barfuss et al., 2016). Also used to convert clique and separator structure from MFCF into partial correlation and precision matrices

Usage

LoGo(
  data,
  cliques,
  separators,
  normal = TRUE,
  na.data = c("pairwise", "listwise", "fiml", "none"),
  partial = TRUE,
  ...
)

Arguments

data	Must be a dataset
cliques	Cliques defined in the network. Input can be a list or matrix
separators	Separators defined in the network. Input can be a list or matrix
normal	Should data be transformed to a normal distribution? Defaults to TRUE (computes correlations using the cor_auto function). Set to FALSE for Pearson's correlations
na.data	How should missing data be handled? For "listwise" deletion the na.omit function is applied. Set to "fiml" for Full Information Maximum Likelihood (corFiml). Full Information Maximum Likelihood is recommended but time consuming
partial	Should the output network's connections be the partial correlation between two nodes given all other nodes? Defaults to TRUE, which returns a partial correlation matrix. Set to FALSE for a sparse inverse covariance matrix
...	Additional arguments (deprecated arguments)

Value

Returns the sparse LoGo-filtered inverse covariance matrix (partial = FALSE) or LoGo-filtered partial correlation matrix (partial = TRUE)

Author(s)

Alexander Christensen <[e-mail]>

References

Barfuss, W., Massara, G. P., Di Matteo, T., & Aste, T. (2016). Parsimonious modeling with information filtering networks. Physical Review E, 94, 062306.

Examples

# normal set to FALSE for CRAN tests
LoGonet <- LoGo(neoOpen, normal = FALSE, partial = TRUE)

NetworkToolbox documentation built on May 28, 2021, 5:11 p.m.