Sangdon Lee wrote: > Dear All, > > I remember but could not find references showing the relationship > between the Mahalanobis distance and principal component analysis. I > appreciate if anybody explain or give references.
Mahalanobis distance is equal to the T-squared value from PCA when all possible dimensions are used. > Also, I'm wondering what is the right way of clustering observations > when variables are highly collinear? > 1) Run PCA and use all of principal components for cluster analysis > 2) Use the Mahalanobis distance. You don't really want to use Mahalanobis distance by itself for clustering. Mahalanobis distance does not take into account the direction from the mean, it only gives you the distance. So if you cluster by Mahalanobis, you could wind up putting two items together that are opposite directions from the mean -- Paige Miller Eastman Kodak Company [EMAIL PROTECTED] http://www.kodak.com "It's nothing until I call it!" -- Bill Klem, NL Umpire "When you get the choice to sit it out or dance, I hope you dance" -- Lee Ann Womack . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
