-
Involves a mathematical procedure that transforms a set of
correlated response variables inot a smaller set of
uncorrelated variables called principal components
-
For many data analysis problems, PCA can be recommended as a
first step
-
Helpful in dimesionality reduction- discovering the true
dimensionality of the data
-
Eigenvectors of the variance-covariance matrix are used to
define the principal components and are normalized to
have a length 1
-
Transformation is linear- original distances are preserved