NetworkToolbox (version 1.1.1)

LoGo: Local/Global Sparse Inverse Covariance Matrix

Description

Applies the Local/Global method to estimate the sparse inverse covariance matrix using a TMFG-filtered network (see and cite Barfuss et al., 2016)

Usage

LoGo(data, partial = FALSE, normal = FALSE, na.data = c("pairwise",
  "listwise", "fiml", "none"), graphical = FALSE)

Arguments

data

Must be a dataset

partial

Should the output network's connections be the partial correlation between two nodes given all other nodes? Defaults to FALSE, which returns a sparse inverse covariance matrix. Set to TRUE for a partial correlation matrix

normal

Should data be transformed to a normal distribution? Defaults to FALSE. Data is not transformed to be normal. Set to TRUE if data should be transformed to be normal (computes correlations using the cor_auto function from the qgraph package)

na.data

How should missing data be handled? For "listwise" deletion the na.omit function is applied. Set to "fiml" for Full Information Maxmimum Likelihood (psych package). Full Information Maxmimum Likelihood is recommended but time consuming

graphical

Should network be checked for graphical modeling? Defaults to FALSE. Set to TRUE to determine if model is graphical

Value

Returns a list containing the TMFG-filtered matrix (tmfg), and the sparse TMFG-filtered inverse covariance matrix (logo)

References

Barfuss, W., Massara, G. P., Di Matteo, T., & Aste, T. (2016). Parsimonious modeling with information filtering networks. Physical Review E, 94(6), 062306.

Examples

# NOT RUN {
LoGonet<-LoGo(neoOpen, partial = TRUE)$logo

TMFGnet<-LoGo(neoOpen)$tmfg
# }