When individuals are described by one set of variables, several methods are available depending on the types of variables considered (numerical or categorical variables):
- When variables are numericals one can perform a PCA (Principal components analysis).
- When the individuals are described by two categorical variables, one can obtained a contingency table and then perform a CA (Correspondence Analysis).
- When individuals are described by a set of categorical variables one can perform a MCA (Multiple Correspondence Analysis).
In all these analyses, one can use supplementary rows and columns.
Each method will be illustrated by a precise example, PCA being the more detailed one.
The HCPC (Hierarchical Clustering on Principal Components) function allows to perform a clustering on individuals. This function combines principal components methods, hierarchical clustering and partitioning to better visualize and highlight the similarities between individuals.