I understand that the quality of representation of an individual by a certain axis is measured by the cosine of the angle between the axis and the individual; the more the vector representing the individual is "close" to the axis the more the latter represents better the former. However, I found it challenging to understand the concept behind the quality of representation of a variable. I tried scanning through Making sense of principal component analysis, eigenvectors & eigenvalues but didn't find anything related. The word "quality" isn't even mentioned in the post. I also tried to search elsewhere but to no avail.
Add a comment
|