Geometric Data Analysis and other descriptive techniques

GDAtools provides functions for Geometric Data Analysis :

  • specific Multiple Correspondence Analysis (speMCA)
  • Class Specific Analysis (csMCA)
  • Multiple Factor Analysis (multiMCA)
  • “standardized” Multiple Correspondence Analysis (stMCA)
  • guides for interpretation (test-values, contributions, etc.)
  • inductive tests
  • analysis of structuring factors (concentration ellipses, interactions, etc.)
  • graphical representations (with and without ggplot2)

Besides, it also provides :

  • several functions for bivariate associations between variables (phi coefficients, Cramer’s V, correlation coefficients, eta-squared, etc.),
  • plotting functions for bivariate associations between variables,
  • the translation of logit models coefficients into percentages,
  • weighted contingency tables,
  • an underrated association measure for contingency tables (“Percentages of Maximum Deviation from Independence”, aka PEM).


Please visit for documentation


Execute the following code within R:

if (!require(devtools)){


Bry X., Robette N., Roueff O., 2016, « A dialogue of the deaf in the statistical theater? Adressing structural effects within a geometric data analysis framework », Quality & Quantity, 50(3), pp 1009–1020 []

Le Roux B. and Rouanet H., 2010, Multiple Correspondence Analysis, SAGE, Series: Quantitative Applications in the Social Sciences, Volume 163, CA:Thousand Oaks.

Le Roux B. and Rouanet H., 2004, Geometric Data Analysis: From Correspondence Analysis to Stuctured Data Analysis, Kluwer Academic Publishers, Dordrecht.

Deauvieau J., 2019, « Comparer les resultats d’un modele logit dichotomique ou polytomique entre plusieurs groupes a partir des probabilites estimees », Bulletin de Methodologie Sociologique, 142(1), 7-31.

Cibois P., 1993, « Le PEM, pourcentage de l’ecart maximum : un indice de liaison entre modalites d’un tableau de contingence », Bulletin de Methodologie Sociologique, 40, pp 43-63, []

Rakotomalala R., « Comprendre la taille d’effet (effect size) », []