Hello
i need some precision about nipals in the chemometrics package in R .
When i use nipals in chemometrics i obtain T and P matrix.
I really don't understand what to do with these two matrix to obtain
the scores for every the component (like in spss fo example)
Comp1 Comp2 Comp3
quest1 0,8434 0,54333 0,3466
quest2 0,665 0,7655 0,433
Thank you very much for your help
(I know that X=TP+E)... But don't understand else....
nipals in the chemometrics package in R
8 messages · Bryan Hanson, Jeff Newmiller, Pedro Mardones +1 more
zz dd: If you want a typical score plot, say PC1 vs PC2, then plot the first and second columns of your score matrix (T) against each other and label the points with the row names (if available) or create a text label from where ever you have this information stored. To get an unlabeled score plot, you could simply do: plot(T[,1], T[,2]) If you are using the package chemometrics, you should take a look at the book that goes with it too: Varmuza and Filzmoser, "Multivariate Statistical Analysis in Chemometrics". If you need more guidance than this, you should probably give us more details about what you are doing. Bryan **************** Prof. Bryan Hanson Dept of Chemistry & Biochemistry DePauw University Greencastle IN 46135 USA academic.depauw.edu/~hanson/deadpezsociety.html github.com/bryanhanson academic.depauw.edu/~hanson/UMP/Index.html
On Dec 1, 2011, at 6:51 AM, zz dd wrote:
Hello
i need some precision about nipals in the chemometrics package in R .
When i use nipals in chemometrics i obtain T and P matrix.
I really don't understand what to do with these two matrix to obtain
the scores for every the component (like in spss fo example)
Comp1 Comp2 Comp3
quest1 0,8434 0,54333 0,3466
quest2 0,665 0,7655 0,433
Thank you very much for your help
(I know that X=TP+E)... But don't understand else....
______________________________________________ R-help at r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
3 days later
An embedded and charset-unspecified text was scrubbed... Name: not available URL: <https://stat.ethz.ch/pipermail/r-help/attachments/20111205/48287e1a/attachment.pl>
This is not a homework help list.
---------------------------------------------------------------------------
Jeff Newmiller The ..... ..... Go Live...
DCN:<jdnewmil at dcn.davis.ca.us> Basics: ##.#. ##.#. Live Go...
Live: OO#.. Dead: OO#.. Playing
Research Engineer (Solar/Batteries O.O#. #.O#. with
/Software/Embedded Controllers) .OO#. .OO#. rocks...1k
---------------------------------------------------------------------------
Sent from my phone. Please excuse my brevity.
zz dd <void1999 at gmail.com> wrote:
Hello The solution maybe there but i need to compute it into R if someone can help me : (Previously store score vector t in score matrix T; store loading vector p in loading matrix P) that's done by nipals in chemometrics After use of nipals function you have T and P matrix First : "Calculate the residual matrix of X. Stop if the elements of Xres are very small because no further PCA components are reasonable" : Xres= X-u.b(T) u : improved score vector b: loading vector X : a mean-centered matrix Second : Replace X with Xres and continue with step 2 (with nipals chemometrics...) for calculation of the next PCA component. If someone can help me ? Thank's a lot 2011/12/1 zz dd <void1999 at gmail.com>
Hello
i need some precision about nipals in the chemometrics package in R .
When i use nipals in chemometrics i obtain T and P matrix.
I really don't understand what to do with these two matrix to obtain
the scores for every the component (like in spss fo example)
Comp1 Comp2 Comp3
quest1 0,8434 0,54333 0,3466
quest2 0,665 0,7655 0,433
Thank you very much for your help
(I know that X=TP+E)... But don't understand else....
[[alternative HTML version deleted]]
______________________________________________ R-help at r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
An embedded and charset-unspecified text was scrubbed... Name: not available URL: <https://stat.ethz.ch/pipermail/r-help/attachments/20111205/338d8bbc/attachment.pl>
Perhaps you can try the examples given in http://www.jstatsoft.org/v18/i02 for getting a better idea about how the NIPALS algorithm works. BTW, yes,it looks like a homework question specially when your user name is "zz dd <void1999 at gmail.com>" so you can't be recognized.
On Mon, Dec 5, 2011 at 9:27 AM, zz dd <void1999 at gmail.com> wrote:
Thank you for your brevity you don't have to say more things to show who you are. Else if you don't understand what we are talking about, you shouldn't ?be rude and insulting. May be you are quite young please take time to read Nonaka and Takeuchi and moreover Takanashi to uderstand the way to go from information to knowledge to wisdom that's quite useful for IS / IT and should bring you a bit of etiquette. *I have a dream* *that one day this nation will rise up and live out the true meaning of its creed : ?We hold these truths to be self-evident : that all men are created equal.?* Have a nice day. 2011/12/5 Jeff Newmiller <jdnewmil at dcn.davis.ca.us>
This is not a homework help list. --------------------------------------------------------------------------- Jeff Newmiller ? ? ? ? ? ? ? ? ? ? ? ?The ? ? ..... ? ? ? ..... ?Go Live... DCN:<jdnewmil at dcn.davis.ca.us> ? ? ? ?Basics: ##.#. ? ? ? ##.#. ?Live Go... ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ?Live: ? OO#.. Dead: OO#.. ?Playing Research Engineer (Solar/Batteries ? ? ? ? ? ?O.O#. ? ? ? #.O#. ?with /Software/Embedded Controllers) ? ? ? ? ? ? ? .OO#. ? ? ? .OO#. ?rocks...1k --------------------------------------------------------------------------- Sent from my phone. Please excuse my brevity. zz dd <void1999 at gmail.com> wrote:
Hello The solution maybe there but i need to compute it into R if someone can help me : (Previously store score vector t in score matrix T; store loading vector p in loading matrix P) that's done by nipals in chemometrics After use of nipals function you have T and P matrix First : "Calculate the residual matrix of X. Stop if the elements of Xres are very small because no further PCA components are reasonable" : Xres= X-u.b(T) u : improved score vector b: loading vector X : a mean-centered matrix Second : Replace X with Xres and continue with step 2 (with nipals chemometrics...) for calculation of the next PCA component. If someone can help me ? Thank's a lot 2011/12/1 zz dd <void1999 at gmail.com>
Hello i need some precision about nipals in the chemometrics package in R . When i use nipals in chemometrics i obtain T and P matrix. I really don't understand what to do with these two matrix to obtain the scores for every the component (like in spss fo example) ? ? ? ? ? ? Comp1 ? ?Comp2 ? Comp3 quest1 0,8434 ? ? ?0,54333 ? 0,3466 quest2 0,665 ? ? ? 0,7655 ? ? ?0,433 Thank you very much for your help (I know that X=TP+E)... But don't understand else....
? ? ? [[alternative HTML version deleted]]
______________________________________________ R-help at r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
? ? ? ?[[alternative HTML version deleted]]
______________________________________________ R-help at r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
An embedded and charset-unspecified text was scrubbed... Name: not available URL: <https://stat.ethz.ch/pipermail/r-help/attachments/20111205/57bcb2f1/attachment.pl>
An embedded and charset-unspecified text was scrubbed... Name: not available URL: <https://stat.ethz.ch/pipermail/r-help/attachments/20111205/e5874741/attachment.pl>