Gottfried Helms wrote: > Paige Miller schrieb: > >>... >>I am wondering if you have tried the NIPALS algorithm, and how it >>compares (both in terms of accuracy and in terms of computer resources >>and time used) to the algorithm you describe. The NIPALS algorithm gives > > > Paige - > > this sounds interesting. But besides of following your references - is > it possible to give a short insight in the principle of this NIPALS-algorithm? > > Gottfried
NIPALS is an iterative method that will find eigencvectors and eigenvalues from a given X matrix. Allow me to quote from the article Wold, S., Esbensen, K. and Geladi, P. (1987) "Principal Component Analysis", Chemometrics and Intelligent Laboratory Systems, 37-52 "Hence p (as defined in the algorithm) is an eigenvector to X'X with the eigenvalue t't/c and we see that the NIPALS algorithm is a variant of the power method used for matrix diagonalization (see, e.g. Golub and Van Loan)." Hope that helps -- Paige Miller [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/ . =================================================================
