[R] PCA - scores

William Revelle lists at revelle.net
Fri Mar 4 18:33:11 CET 2011


At 9:52 AM -0700 3/4/11, Shari Clare wrote:
>Hi Bill and Josh:
>
>When I run any "principal" code with scores=TRUE, I get the following Error:
>
>Error in principal (my.data,3,scores=TRUE) : unused argument (scores=TRUE)
>
>
>Thoughts?

What version of psych are you using?

Does it work on the example I sent (see below)?



>
>Thanks,
>Shari
>
>
>
>
>
>
>On 3-Mar-11, at 9:42 PM, William Revelle wrote:
>
>>Shari,
>>  Josh partly answered your question, but his example did not 
>>include rotation because he took out just one factor.
>>
>>Try:
>>
>>require(psych)
>>mt.pc <- principal(mtcars,3,scores=TRUE)   #this gives you the 
>>varimax rotated first 3 principal components
>>#pc.scores <- mt.pc$scores     #here are the scores
>>
>>biplot(mt.pc)    #show the data as well as the principal components 
>>in a biplot
>>
>>
>>
>>Bill
>>
>>
>>At 5:15 PM -0800 3/3/11, Joshua Wiley wrote:
>>
>>>Hi Shari,
>>>
>>>
>>>Yes, please look at the documentation for principal.  You can access
>>>
>>>this (assuming you have loaded psych) by typing at the console:
>>>
>>>
>>>?principal
>>>
>>>
>>>note the logical argument "scores".
>>>
>>>
>>>Here is a small example:
>>>
>>>
>>>##############################
>>>
>>>require(psych)
>>>
>>>require(GPArotation)
>>>
>>>
>>>dat <- principal(mtcars[, c("mpg", "hp", "wt")], nfactors = 1,
>>>
>>>  rotate = "oblimin", scores = TRUE)
>>>
>>>
>>>dat$scores
>>>
>>>##############################
>>>
>>>
>>>Cheerio,
>>>
>>>
>>>Josh
>>>
>>>
>>>On Thu, Mar 3, 2011 at 1:02 PM, Shari Clare 
>>><<mailto:sclare at ualberta.ca>sclare at ualberta.ca> wrote:
>>>
>>>>I am running a PCA, but would like to rotate my data and limit the
>>>>
>>>>number of factors that are analyzed.  I can do this using the
>>>>
>>>>"principal" command from the psych package [principal(my.data,
>>>>
>>>>nfactors=3,rotate="varimax")], but the issue is that this does not
>>>>
>>>>report scores for the Principal Components the way "princomp" does.
>>>>
>>>>
>>>>My question is:
>>>>
>>>>
>>>>Can you get an output of scores using "principal" OR, is there a way
>>>>
>>>>to limit the number of factors that are included when you use
>>>>
>>>>"princomp"?
>>>>
>>>>
>>>>Thanks,
>>>>
>>>>Shari Clare
>>>>
>>>>
>>>>PhD Candidate
>>>>
>>>>Department of Renewable Resources
>>>>
>>>>University of Alberta
>>>>
>>>><mailto:sclare at ualberta.ca>sclare at ualberta.ca
>>>>
>>>>780-492-2540
>>>>
>>>>
>>>>
>>>>
>>>>
>>>>
>>>>
>>>>
>>>>
>>>>        [[alternative HTML version deleted]]
>>>>
>>>>
>>>>______________________________________________
>>>>
>>>><mailto:R-help at r-project.org>R-help at r-project.org mailing list
>>>>
>>>><https://stat.ethz.ch/mailman/listinfo/r-help>https://stat.ethz.ch/mailman/listinfo/r-help
>>>>
>>>>PLEASE do read the posting guide 
>>>><http://www.R-project.org/posting-guide.html>http://www.R-project.org/posting-guide.html
>>>>
>>>>and provide commented, minimal, self-contained, reproducible code.
>>>>
>>>>
>>>
>>>
>>>
>>>--
>>>
>>>Joshua Wiley
>>>
>>>Ph.D. Student, Health Psychology
>>>
>>>University of California, Los Angeles
>>>
>>><http://www.joshuawiley.com/>http://www.joshuawiley.com/
>>>
>>>
>>>______________________________________________
>>>
>>><mailto:R-help at r-project.org>R-help at r-project.org mailing list
>>>
>>><https://stat.ethz.ch/mailman/listinfo/r-help>https://stat.ethz.ch/mailman/listinfo/r-help
>>>
>>>PLEASE do read the posting guide 
>>><http://www.R-project.org/posting-guide.html>http://www.R-project.org/posting-guide.html
>>>
>>>and provide commented, minimal, self-contained, reproducible code.



More information about the R-help mailing list