@ARTICLE{10.21494/ISTE.OP.2018.0311, TITLE={Clustering of variables and multivariate analysis of mixed data from BCI study}, AUTHOR={Jérôme Saracco, Marie Chavent, Liliana Audin-Garcia, Véronique Lespinet-Najib, Ricardo Ron-Angevin, }, JOURNAL={Cognitive Engineering}, VOLUME={2}, NUMBER={Issue 1}, YEAR={2018}, URL={https://openscience.fr/Clustering-of-variables-and-multivariate-analysis-of-mixed-data-from-BCI-study}, DOI={10.21494/ISTE.OP.2018.0311}, ISSN={2517-6978}, ABSTRACT={The aim of this work is to analyze complex data from a Brain Computer Interfaces (BCI) study using multivariate statistical methods (PCAmix approach and clustering of variables) to better understand and interpret their relationships. This article presents clustering of variables which aim is to lump together strongly related variables. The proposed approach works on a mixed data set, i.e. on a data set which contains numerical variables and categorical variables. Two algorithms of clustering of variables are described : a hierarchical clustering and a k-means type clustering. A brief description of PCAmix method (that is a principal component analysis for mixed data) is provided, since the calculus of the synthetic variables summarizing the obtained clusters of variables is based on this multivariate method. Finally, the PCAmix and ClustOfVar approaches (implemented in the R packages ClustOfVar and PCAmixdata) are illustrated on a real dataset from a BCI (brain computer interface) study. Recommendations, based not only on performance, efficiency, but also on satisfaction criteria, could be made concerning the choice of interface in the use of virtual keyboards, especially for people with motor disorder such as Charcot’s disease.}}