![EGAnet logo](reference/figures/EGAnet_hex_2.png)

The {EGAnet} package is the primary source for implementing the
Exploratory Graph Analysis (EGA) framework in R.

The goal of the package is to provide:

- state-of-the-art network psychometrics methods

- fast, reproducible code

- beautiful, publication-ready visualizations

*Check out [what’s changed](https://r-ega.net/articles/whats-changed.md)
in version +2.0.0*

How to Install

    install.packages("EGAnet")

    if(!"devtools" %in% unlist(lapply(.libPaths(), list.files))){
      install.packages("devtools")
    }

    devtools::install_github("hfgolino/EGAnet")

Contact

[Hudson F. Golino](https://psychology.as.virginia.edu/golino)  
Associate Professor of Quantitative Methods  
Department of Psychology  
University of Virginia  
<hfg9s@virginia.edu>  
[](https://twitter.com/GolinoHudson)
[](https://scholar.google.com/citations?user=Ris_otUAAAAJ&hl=en&oi=ao)

[Alexander P.
Christensen](https://www.vanderbilt.edu/psychological_sciences/bio/alexander-christensen)  
Assistant Professor of Quantitative Methods  
Department of Psychology and Human Development  
Vanderbilt University  
<alexpaulchristensen@gmail.com>  
[](https://scholar.google.com/citations?user=RbatznQAAAAJ&hl=en&oi=ao)

Support

The {EGAnet} package is currently supported by two University of
Virginia grants, one from the STAR - [Support Transformative Autism
Research](https://curry.virginia.edu/faculty-research/centers-labs-projects/supporting-transformative-autism-research-star)
initiative and one from the [Democracy
Initiative](https://democracyinitiative.virginia.edu).

# Package index

## EGA Functions

Main Exploratory Graph Analysis functions

- [`bootEGA()`](https://r-ega.net/reference/bootEGA.md) : Bootstrap
  Exploratory Graph Analysis

- [`dynEGA()`](https://r-ega.net/reference/dynEGA.md) : Dynamic
  Exploratory Graph Analysis

- [`dynEGA.ind.pop()`](https://r-ega.net/reference/dynEGA.ind.pop.md) :

  Intra- and Inter-individual
  [`dynEGA`](https://r-ega.net/reference/dynEGA.html)

- [`EGA()`](https://r-ega.net/reference/EGA.md) : Exploratory Graph
  Analysis

- [`EGA.estimate()`](https://r-ega.net/reference/EGA.estimate.md) :

  Estimates [`EGA`](https://r-ega.net/reference/EGA.html) for
  Multidimensional Structures

- [`EGA.fit()`](https://r-ega.net/reference/EGA.fit.md) :

  [`EGA`](https://r-ega.net/reference/EGA.html) Optimal Model Fit using
  the Total Entropy Fit Index
  ([`tefi`](https://r-ega.net/reference/tefi.html))

- [`hierEGA()`](https://r-ega.net/reference/hierEGA.md) :

  Hierarchical [`EGA`](https://r-ega.net/reference/EGA.html)

- [`riEGA()`](https://r-ega.net/reference/riEGA.md) :

  Random-Intercept [`EGA`](https://r-ega.net/reference/EGA.html)

## EGA Psychometric Functions

Exploratory Graph Analysis network psychometric framework functions

- [`CFA()`](https://r-ega.net/reference/CFA.md) :

  CFA Fit of [`EGA`](https://r-ega.net/reference/EGA.html) or
  [`hierEGA`](https://r-ega.net/reference/hierEGA.html) Structure

- [`dimensionStability()`](https://r-ega.net/reference/dimensionStability.md)
  :

  Dimension Stability Statistics from
  [`bootEGA`](https://r-ega.net/reference/bootEGA.html)

- [`dynamic.network.compare()`](https://r-ega.net/reference/dynamic.network.compare.md)
  : Compares Dynamic Network Structures Using Permutation

- [`invariance()`](https://r-ega.net/reference/invariance.md) :

  Measurement Invariance of
  [`EGA`](https://r-ega.net/reference/EGA.html) Structure

- [`itemDiagnostics()`](https://r-ega.net/reference/itemDiagnostics.md)
  : Diagnostics Analysis for Low Stability Items

- [`itemStability()`](https://r-ega.net/reference/itemStability.md) :

  Item Stability Statistics from
  [`bootEGA`](https://r-ega.net/reference/bootEGA.html)

- [`LCT()`](https://r-ega.net/reference/LCT.md) : Loadings Comparison
  Test

- [`net.loads()`](https://r-ega.net/reference/net.loads.md) : Network
  Loadings

- [`net.scores()`](https://r-ega.net/reference/net.scores.md) : Network
  Scores

- [`network.fit()`](https://r-ega.net/reference/network.fit.md) :
  Traditional Fit Metrics for Networks

- [`UVA()`](https://r-ega.net/reference/UVA.md) : Unique Variable
  Analysis

## EGM Functions

Main Exploratory Graph Model functions

- [`EGM()`](https://r-ega.net/reference/EGM.md) : Exploratory Graph
  Model

- [`EGM.compare()`](https://r-ega.net/reference/EGM.compare.md) :

  Compare `EGM` with EFA

- [`simEGM()`](https://r-ega.net/reference/simEGM.md) :

  Simulate data following a Exploratory Graph Model (`EGM`)

## Information Theory Functions

Information Theory-related functions for network psychometrics

- [`boot.ergoInfo()`](https://r-ega.net/reference/boot.ergoInfo.md) :
  Bootstrap Test for the Ergodicity Information Index

- [`entropyFit()`](https://r-ega.net/reference/entropyFit.md) : Entropy
  Fit Index

- [`ergoInfo()`](https://r-ega.net/reference/ergoInfo.md) : Ergodicity
  Information Index

- [`genTEFI()`](https://r-ega.net/reference/genTEFI.md) : Generalized
  Total Entropy Fit Index using Von Neumman's entropy (Quantum
  Information Theory) for correlation matrices

- [`infoCluster()`](https://r-ega.net/reference/infoCluster.md) :

  Information Theoretic Mixture Clustering for
  [`dynEGA`](https://r-ega.net/reference/dynEGA.html)

- [`information()`](https://r-ega.net/reference/information.md) :
  Information Theory Metrics

- [`jsd()`](https://r-ega.net/reference/jsd.md) : Jensen-Shannon
  Distance

- [`tefi()`](https://r-ega.net/reference/tefi.md) : Total Entropy Fit
  Index using Von Neumman's entropy (Quantum Information Theory) for
  correlation matrices

- [`tefi.compare()`](https://r-ega.net/reference/tefi.compare.md) :

  Compare Total Entropy Fit Index
  ([`tefi`](https://r-ega.net/reference/tefi.html)) Between Two
  Structures

- [`totalCor()`](https://r-ega.net/reference/totalCor.md) : Total
  Correlation

- [`totalCorMat()`](https://r-ega.net/reference/totalCorMat.md) : Total
  Correlation Matrix

- [`vn.entropy()`](https://r-ega.net/reference/vn.entropy.md) : Entropy
  Fit Index using Von Neumman's entropy (Quantum Information Theory) for
  correlation matrices

## Plots

Plot-related functions

- [`color_palette_EGA()`](https://r-ega.net/reference/color_palette_EGA.md)
  :

  [`EGA`](https://r-ega.net/reference/EGA.html) Color Palettes

- [`compare.EGA.plots()`](https://r-ega.net/reference/compare.EGA.plots.md)
  :

  Visually Compare Two or More `EGAnet` plots

- [`plot_clusters()`](https://r-ega.net/reference/plot_clusters.md) :
  Plot Clustered Individual Networks

- [`EGAnet-plot`](https://r-ega.net/reference/EGAnet-plot.md)
  [`plot.EGAnet`](https://r-ega.net/reference/EGAnet-plot.md) :

  S3 Plot Methods for `EGAnet`

## Basic Functions

General purpose functions that allow for a more modular usage

- [`auto.correlate()`](https://r-ega.net/reference/auto.correlate.md) :
  Automatic correlations

- [`community.compare()`](https://r-ega.net/reference/community.compare.md)
  : Compares Community Detection Solutions Using Permutation

- [`community.consensus()`](https://r-ega.net/reference/community.consensus.md)
  : Applies the Consensus Clustering Method (Louvain only)

- [`community.detection()`](https://r-ega.net/reference/community.detection.md)
  : Apply a Community Detection Algorithm

- [`community.homogenize()`](https://r-ega.net/reference/community.homogenize.md)
  : Homogenize Community Memberships

- [`community.unidimensional()`](https://r-ega.net/reference/community.unidimensional.md)
  : Approaches to Detect Unidimensional Communities

- [`convert2igraph()`](https://r-ega.net/reference/convert2igraph.md) :

  Convert networks to `igraph`

- [`convert2tidygraph()`](https://r-ega.net/reference/convert2tidygraph.md)
  :

  Convert networks to `tidygraph`

- [`cosine()`](https://r-ega.net/reference/cosine.md) : Cosine
  similarity

- [`EBICglasso.qgraph()`](https://r-ega.net/reference/EBICglasso.qgraph.md)
  :

  [`EBICglasso`](https://rdrr.io/pkg/qgraph/man/EBICglasso.html) from
  `qgraph` 1.4.4

- [`Embed()`](https://r-ega.net/reference/Embed.md) : Time-delay
  Embedding

- [`frobenius()`](https://r-ega.net/reference/frobenius.md) : Frobenius
  Norm (Similarity)

- [`glla()`](https://r-ega.net/reference/glla.md) : Generalized Local
  Linear Approximation

- [`igraph2matrix()`](https://r-ega.net/reference/igraph2matrix.md) :

  Convert network to matrix

- [`known.graph()`](https://r-ega.net/reference/known.graph.md) : Re-fit
  Network

- [`modularity()`](https://r-ega.net/reference/modularity.md) : Computes
  the (Signed) Modularity Statistic

- [`network.compare()`](https://r-ega.net/reference/network.compare.md)
  : Compares Network Structures Using Permutation

- [`network.estimation()`](https://r-ega.net/reference/network.estimation.md)
  : Apply a Network Estimation Method

- [`network.nonconvex()`](https://r-ega.net/reference/network.nonconvex.md)
  : GLASSO with Non-convex Penalties

- [`network.generalizability()`](https://r-ega.net/reference/network.generalizability.md)
  : Estimate the Generalizability of Network

- [`network.predictability()`](https://r-ega.net/reference/network.predictability.md)
  : Predict New Data based on Network

- [`network.regularization()`](https://r-ega.net/reference/network.regularization.md)
  : Regularized Networks with Convex and Non-convex Penalties

- [`polychoric.matrix()`](https://r-ega.net/reference/polychoric.matrix.md)
  : Computes Polychoric Correlations

- [`simDFM()`](https://r-ega.net/reference/simDFM.md) : Simulate data
  following a Dynamic Factor Model

- [`TMFG()`](https://r-ega.net/reference/TMFG.md) : Triangulated
  Maximally Filtered Graph

- [`wto()`](https://r-ega.net/reference/wto.md) : Weighted Topological
  Overlap

## Data and Package Information

Data hosted in the {EGAnet} package

- [`EGAnet`](https://r-ega.net/reference/EGAnet-package.md)
  [`EGAnet-package`](https://r-ega.net/reference/EGAnet-package.md) :
  EGAnet-package

- [`boot.wmt`](https://r-ega.net/reference/boot.wmt.md) :

  [`bootEGA`](https://r-ega.net/reference/bootEGA.html) Results of
  [`wmt2`](https://r-ega.net/reference/wmt2.html)Data

- [`depression`](https://r-ega.net/reference/depression.md) : Depression
  Data

- [`dnn.weights`](https://r-ega.net/reference/dnn.weights.md) : Loadings
  Comparison Test Deep Learning Neural Network Weights

- [`ega.wmt`](https://r-ega.net/reference/ega.wmt.md) :

  [`EGA`](https://r-ega.net/reference/EGA.html) Network of
  [`wmt2`](https://r-ega.net/reference/wmt2.html)Data

- [`intelligenceBattery`](https://r-ega.net/reference/intelligenceBattery.md)
  : Intelligence Data

- [`optimism`](https://r-ega.net/reference/optimism.md) : Optimism Data

- [`prime.num`](https://r-ega.net/reference/prime.num.md) : Prime
  Numbers through 100,000

- [`sim.dynEGA`](https://r-ega.net/reference/sim.dynEGA.md) : sim.dynEGA
  Data

- [`wmt2`](https://r-ega.net/reference/wmt2.md) : WMT-2 Data

# Articles

### Tutorials

- [Quick Start](https://r-ega.net/articles/quick-start.md):
- [EGA + Transformers NLP](https://r-ega.net/articles/ega-nlp.md):
- [Using External Networks (and external
  packages)](https://r-ega.net/articles/modular-approach.md):
- [Plotting with {EGAnet}](https://r-ega.net/articles/plotting.md):

### Workflows

- [Exploratory Graph Analysis](https://r-ega.net/articles/ega.md):

### Inner Workings

- [What's Changed?](https://r-ega.net/articles/whats-changed.md):
- [Argument
  Passing](https://r-ega.net/articles/argument-flexibility.md):
- [Reproducibility and Pseudorandom Number Generation
  (PRNG)](https://r-ega.net/articles/reproducibility-prng.md):
- [Errors](https://r-ega.net/articles/errors.md):

### Resources

- [Publications](https://r-ega.net/articles/research.md):
- [Teaching](https://r-ega.net/articles/teaching.md):