Here is the link: http://commanber.com/2017/06/17/sample-variance/

I will remove my article immediately if you do not allow me to release the Chinese version of your article.

Thanks very much!

Have a good day! ]]>

I had one doubt about equation 2. Shouldn’t there be only one distance from a sample point to a centroid? How can there be two distances i.e minimum and maximum distances?

]]>Consider \Sigma = [2 0.1; 0.1 3]; If you perform an eigenvalue-eigenvector decomposition, i.e. P = VLV^T. The V obtained is no longer a rotation matrix. It is orthogonal but not a rotation matrix. I think Niranjan Kotha sees the same issue. The problem is that the factorization doesn’t always yield a rotation matrix (orthogonal yes, but not the special orthogonal matrix).

]]>It looks like there is a typo in the 2nd line while deriving equation (6). The lambda square should have a positive sign.

]]>