Methods and Measures for Brain, Cognitive, and Psychometric Network Analysis

Implements network analysis and graph theory measures used in neuroscience, cognitive science, and psychology. Methods include various filtering methods and approaches such as threshold, dependency (Kenett, Tumminello, Madi, Gur-Gershgoren, Mantegna, & Ben-Jacob, 2010 ), Information Filtering Networks (Barfuss, Massara, Di Matteo, & Aste, 2016 ), and Efficiency-Cost Optimization (Fallani, Latora, & Chavez, 2017 ). Brain methods include the recently developed Connectome Predictive Modeling (see references in package). Also implements several network measures including local network characteristics (e.g., centrality), community-level network characteristics (e.g., community centrality), global network characteristics (e.g., clustering coefficient), and various other measures associated with the reliability and reproducibility of network analysis.


Changes in version 1.2.3

o removed isSym function

o fixed bugs in degree, strength, hybrid, and edgerep functions (symmetric matrix check is fixed)

o naming order bug fix in comcat

o removed bootgen and bootgen.plot functions (experimental funcitons that may return later)

o updated several functions' documentation

Changes in version 1.2.2

o comcat: added functionality to compute connectivity across communities or for each community

o stable: added closeness centrality

o desc: descriptive statistics function for a single variable

o desc.all: descriptive statistics function for a dataset

Changes in version 1.2.1

o updated comm.close algorithm: takes the reciprocal of the mean ASPL of each community

o LoGo: removed some arguments, added "..." for deprecated arguments (e.g., standardize)

o rep.resp: function to detect repetitive responding

Changes in version 1.2.0

o net.coverage: a function to examine the coverage of a subset of nodes in the network

o comm.close: a function to estimate the closeness centrality of communities in the network

o comm.eigen: a function to estimate the eigenvector centrality of communities in the network (based on the flow.frac function)

o comm.str: a function to estimate the strength/degree centrality of communities in the network

o flow.frac: a function to estimate the eigenvector centrality of a subset of nodes in the network

o core.items: a function to automatically determine core, intermediate, and peripheral items in the network

o commboot: removed

o removed splitsamp functions (will be brought back in a future update)

o removed options for weighted argument in network construction functions

o bootgenPlot changed to bootgen.plot

o significantly improved documentation and descriptions of all functions

o improved functionality of several functions

o updated citation

Changes in version 1.1.3

o nams: facet means are now adjusted relative to the overall score--improves estimate and makes adjusted means/sums equivalent to overall adjusted score

o edgerep: node label bug fixed

o bootstrapped functions: argument bug fixed

o commboot: unweighted network option added

o updated citation

o semnetboot: removed and moved to package SemNetToolbox

o semnetmeas: removed and moved to package SemNetToolbox

o bugs fixed throughout package

Changes in version 1.1.2

o bootgen: ensures graphical model for method = "LoGo"

o nams: adjusted algorithm

o sim.swn: added a function to simulate small-world networks and data

o PMFG: removed function due to inefficiency

o diversity: added a function to compute the diversity coefficient of nodes in the network

o gateway: added a function to compute the gateway coefficient of nodes in the network

o participation: added a function to compute the participation coefficient of nodes in the network

o edgerep: fixed bug in plot to display the strength of the replicated edges only and will display diagonal if diagonals are equivalent between the two matrices

o nams: added output for an overall network adjusted mean/sum score

o improved documentation

o added EBICglasso and Isingfit to bootgen and commboot function

o added back the kld and rmse function

o added network visualization of canonical and macro-scale region connectivity to cpmIV function

o LoGo: no longer outputs a list (only a matrix) and added a standardize argument for inverse correlation matrix as output (does not change partial correlation output)

Changes in Version 1.1.1

o LoGo: reversed sign bug fixed; cov.shrink no longer used for covariance matrix estimation

o is.graphical: updated with more efficient (inverse) covariance check

o bootgen: uses partial correlation significance for method = "LoGo"

Changes in Version 1.1.0

o new data files: NEO-PI-3 data for psychometric network analysis, verbal fluency files for semantic network analysis, behavioral NEO-PI-3 and an associated brain connectivity array for brain network analysis

o bootgen: no longer produces plots; added is.graphical function to automatically check if network is graphical when method = "LoGo"

o bootgenPlot: output from the bootgen function can now be input into a separate function to obtain plots. Contains an argument to also plot the bootstrapped network generalization method

o bootstrapping functions all include a seeds argument, which can be used to replicate the previous analysis using the Seeds output

o PMFG: now outputs a list to be used in Cytoscape visualization software (sparseList)

o reg: a function to perform regression for a dataset. An argument can set the type of regression and for the matrix to be symmetric

o nams: a function to calculate network adjusted mean or sum for data (based on the hybrid centrality)

o hybrid: added an option for "standard", "random", or "average" betweenness centrality to be used

o cpmIV: parallel processing now available for covariate estimation (defaults to max(cores) - 1)

o LoGo: corpcor's cov.shrink is now used for covariance estimation when argument normal = TRUE; added argument to check if network is graphical

o edgerep: includes a list of the replicated edges and their respective weights in each network. A plot for this information is also available (defaults to FALSE). Also includes an argument "corr" which allows the researcher to select different correlations for examining replicated edge weight relations

o is.graphical: function to check whether the network is graphical

o cor2cov: function to convert correlation matrix into a covariance matrix

o depend: fixed Fisher's z significance test

o kld: removed function

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.


1.4.2 by Alexander Christensen, 8 months ago

Browse source code at

Authors: Alexander Christensen [aut, cre] , Guido Previde Massara [ctb]

Documentation:   PDF Manual  

Task views: Psychometric Models and Methods

GPL (>= 3.0) license

Imports psych, corrplot, fdrtool, R.matlab, igraph, qgraph, ppcor, parallel, foreach, doParallel, MASS, pwr, IsingFit, pbapply

Suggests googledrive

Imported by EGAnet, bootnet.

Suggested by GGMncv.

See at CRAN