|You are working with the text-only light edition of "H.Lohninger: Teach/Me Data Analysis, Springer-Verlag, Berlin-New York-Tokyo, 1999. ISBN 3-540-14743-8". Click here for further information.|
|Table of Contents Appendix Exercises PCR = PCA + MLR|
|See also: PCA, MLR, PCR|
Principal component regression may be carried out as consecutive application of PCA and MLR. Go to the using the data set BENZ which contains spectral information (NMR) and the relative octane numbers for various brands of gasoline .
Try to estimate the octane number (variable ROZ) from the spectral information by using a combination of PCA and MLR. Keep in mind that the principal component analysis should be carried out without the ROZ variable.
Compare the results to the direct application of PCR (which is of course much more convenient).
Last Update: 2005-Jul-16