ABSTRACT
Principal component analysis (PCA) invented in 1901 by Karl Pearson— as a classical data reduction technique, uncovers the interrelationships among many variables. The literature is sparse on PCA used as a reexpression—technique. PCA, viewed as an exploratory data analysis (EDA) technique to identify structure, gives awareness that PCA is a valid (new) data mining tool. This chapter explores PCA as a data mining method, and illustrates PCA as a statistical data mining technique capable of serving in a common application with an expected solution. It provides an original and valuable use of PCA in the construction of quasi-interaction variables, furthering the case of PCA as a powerful data mining method. The chapter also provides the SAS subroutine used in the PCA construction of quasi-interaction variables. It also illustrates PCA in an uncommon application of finding a structural approach for preparing a categorical predictive variable for possible model inclusion.
