Exploring PCA()

PCA() provides great flexibility in its usage. You can choose to ignore some of the original variables or individuals in building a PCA model by supplying PCA() with the ind.sup argument for supplementary individuals and quanti.sup or quali.sup for quantitative and qualitative variables respectively. Supplementary individuals and variables are rows and variables of the original data ignored while building the model.

Your learning objectives in this exercise are:

To conduct PCA considering parts of a dataset
To inspect the most correlated variables with a specified principal component
To find the contribution of variables in the designation of the first 5 principal components

Go for it! The cars dataset is available in your workspace.

Run a PCA on cars by setting the first 8 variables as quantitative supplementary variables and the last 2 variables as qualitative supplementary ones. The graph argument is set to F for not displaying the default graphical output.

Exercise

Exploring PCA()

Instructions 1/4