Using R for Multivariate Analysis
Astrid Jourdan · 2020
R is a programming language oriented toward data analysis, data mining and statistics. This language is based on the notion of vector, which simplifies mathematical calculations and considerably reduces the use of iterative structures. RStudio is an integrated development environment (IDE) specifically created to work with R. This chapter discusses the use of R for the multivariate analysis, focusing of principal component analysis, multiple correspondence analysis, and clustering. The multiple correspondence analysis is run with MCA function and the results are displayed with explor package. Before to run clustering, the quantitative variables should be scaled and the categorical variable CLIMAT and the Error point should be removed. The result of scale function is a matrix. It is necessary to transform it in a dataframe.