Sunday, September 11, 2011

Principal Component Analsis(PCA)

Principal component analysis(PCA)
The first PC1 is set to describe the largest variation in the data, in the direction in which the points spread most in the variable space.
The Score value (ti1) for the point i is the distance from the projection of the point on the 1st component to the origin.
===> PC1 shows its latent variable in a new coordinate system that describes the variation in the data.

No comments:

Post a Comment

Bạn cần thêm thông tin hay có câu hỏi vui lòng comment