Check your understanding
Quiz
You have compressed correlated columns with PCA and factor analysis, clustered with k-means, hierarchical, density-based and mixture methods, chosen and validated the number of groups, mapped high-dimensional data with t-SNE and UMAP, and mined association rules. This quiz checks what stuck. The last two steps are live R you can run.
Question 1 of 6
Why scale before PCA
You should usually standardize variables before running PCA because otherwise:
Correct: PCA maximizes variance, and unscaled large-range variables carry the most raw variance.
Scaling keeps the data numeric.