Overcoming Outliers with ROBPCA

A Guide to Hubert et al.’s Robust PCA Procedure (ROBPCA)

Principal components analysis is a variance decomposition technique that is frequently used for dimensionality reduction. A thorough guide to PCA is available here. In essence, each principal component is computed by finding the linear combination of the original features which has maximal variance, subject to the constraint that it must be orthogonal to the previous principal components. This process tends to be sensitive to outliers as it does not …

apc hands-on-tutorials outliers principal-component