¡Welcome to ExGraf!

ExGraf is a application designed to perform Exploratory Graph Analysis (EGA) to identify the dimensional structure of psychometric data using network-based methods.

What can you do with ExGraf?

  • Data Import: Upload files in .csv or .xlsx format.
  • Item Analysis: Explore descriptive statistics and visualize response distributions using Likert plots.
  • Redundancy Analysis: Identify redundant items within your scale (UVA/wTO-based suggestions).
  • EGA Validation: Analyze and visualize dimensions using network-based methods.
  • Reliability: Assess structural consistency and item stability via Bootstrap EGA.
  • Measurement Invariance: Compare dimensional structures across groups (permutation-based tests).
  • Hierarchical Model (optional): Explore relationships between first- and second-order dimensions.
  • Wording Effects (optional): Detect reverse-worded items that may distort dimensionality (riEGA).
  • Generate Report: Auto-generate academic “Data Analysis” and “Results” sections (requires an OpenAI API key).
  • References: See how to cite ExGraf and find recommended literature.
  • Export R Code: Download reproducible R scripts for each analysis.

⚠️ To properly run the Measurement Invariance, your dataset must include at least one categorical variable (e.g., sex).

Don't have a dataset to test? Download a sample dataset here:

Download sample dataset

Likert Response Plot


Download Settings

EGA Settings

Download Settings

Informative Table


BootEGA Settings

Download Settings

Invariance Settings

Download Settings

Hierarchical EGA

Calculates hierEGA automatically.
Download Settings

Wording Effects

Download Settings

UVA – Variable pairs by wTO cutoffs

Salida equivalente a summary(UVA(datos_actuales)). Se actualiza al retirar ítems.

UVA Summary


Generate Analysis Report with ChatGPT

This section allows you to automatically generate academic methods and results sections using ChatGPT API.

Steps:

  1. Complete your analyses in the previous tabs
  2. Enter your OpenAI API key (get one at OpenAI Platform)
  3. Choose the language for your report
  4. Click "Generate Report" and wait for the results

Note: The app uses the fixed model GPT-4.1.


Your API key is not stored and is only used for this session

Debug Info


                          

                        

                        
                      

                      

                        

                          

                            

                              
Generated Report

                            

                            

                              
Data Analysis Section

                              

                              

                              
Results Section

                              

                              

                              
                              
                            

                          

                          
                        

                      

                      

                        

                          

                            

                              
JSON Data Export

                              

                                
                              

                            

                            

                              

                              

                              
                              

                              

                              
R Code for API Integration

                              

                            

                          

                          
                        

                      

                    

                  

                  
                

              

            

            

              

                

                  

                    

                      
How to Cite ExGraf

                    

                    

              
If you use ExGraf in your research or teaching, please cite it as follows:

              
Ventura-León, J., Lino-Cruz, C., Tocto-Muñoz, S., & Sánchez-Villena, A. R. (2025). ExGraf: A Shiny Interface for Accessible Exploratory Graph Analysis in Psychological and Behavioral Research (Version 1.0) [Shiny application].

              

              
Recommended References

              
    
                
  • Christensen, A. P., Garrido, L. E., & Guerra-Peña, K. (2024). Comparing community detection algorithms in psychometric networks: A Monte Carlo simulation. Behavior Research Methods, 56, 1485–1505. https://doi.org/10.3758/s13428-023-02106-4
    • 
                
  • Christensen, A. P., & Golino, H. (2021). Estimating the stability of psychological dimensions via Bootstrap Exploratory Graph Analysis: A Monte Carlo simulation and tutorial. Psych, 3(3), 479–500. https://doi.org/10.3390/psych3030032
    • 
                
  • Golino, H. F., & Epskamp, S. (2017). Exploratory graph analysis: A new approach for estimating the number of dimensions in psychological research. PLoS ONE, 12(6), e0174035. https://doi.org/10.1371/journal.pone.0174035
    • 
                
  • Jamison, L., Christensen, A. P., & Golino, H. F. (2024). Metric invariance in Exploratory Graph Analysis via permutation testing. Methodology, 20(2), 144–186. https://doi.org/10.5964/meth.12877
    • 
                
  • Jiménez, M., Abad, F. J., García-Garzón, E., Golino, H., Christensen, A. P., & Garrido, L. E. (2023). Dimensionality assessment in bifactor structures with multiple general factors: A network psychometrics approach. Psychological Methods. Advance online publication. https://doi.org/10.1037/met0000590
    •