|
Tutorial: From multivariate to multiway data analysis...an overview |
|
The aim of this tutorial is to present an overview of the main exploratory data analyses used when a great many individuals are described by a great many quantitative and/or categorical variables, when variables are structured according to groups. The methods that will be presented from a geometrical point of view are principal components analysis, multiple correspondence analysis and multiple factor analysis. The concepts of quality of representation, active versus illustrative variable, automatic description of the dimensions provided by (issued from) the analyses will be discussed. Special attention will be paid to real life data and specially data from the genomic field. |
|
|
|
Statisticians who want to invest in exploratory multivariate analysis the “French way”. |