This website uses Cookies. Click Accept to agree to our website's cookie use as described in our Privacy Policy. Click Preferences to customize your cookie settings.
Accept
Reject
Preferences
cancel
Turn on suggestions
Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.
Showing results for 
Show  only  | Search instead for 
Did you mean: 
Submit your abstract to the call for content for Discovery Summit Americas by April 23. Selected abstracts will be presented at Discovery Summit, Oct. 21- 24.
Discovery is online this week, April 16 and 18. Join us for these exciting interactive sessions.
Choose Language Hide Translation Bar
RonB
RonB
Level III

PCA and T-Square T^2

Created: Jul 3, 2018 05:26 AM  |  Last Modified: Jul 3, 2018 05:28 AM (2587 views)

Multivariate Control Chart (from the control chart menu) shows results for Principal Components on Covariances. Doing Principal Components (from the multivariate methodes menu), also on Correlations gives the same eigenvalues and cumulative percentage. Both are scaled.

 

However, the eigenvectors and pc formulas (those that are save to the data table) are not the same.

 

Am I missing something?

 

Thanks

0 Kudos
1 REPLY 1
Bill_Worley
Staff Bill_Worley
Staff

Re: PCA and T-Square T^2

Jul 3, 2018 09:18 AM (2565 views)  |  Posted in reply to message from RonB 07-03-2018

Hello Ron,

 

There is a note at the bottom of the multivariate control chart report that states that the Eigenvectors have been divided by the square root of the Eigenvalues.  This does not happen in the Multivariate Method platform and as best as I can tell this is the difference in results that you are seeing between the two platforms.

 

HTH

Bill