Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

RE: st: RE: FW: Running Polychoric Principal Component Analysis in STATA


From   Cameron McIntosh <cnm100@hotmail.com>
To   STATA LIST <statalist@hsphsun2.harvard.edu>
Subject   RE: st: RE: FW: Running Polychoric Principal Component Analysis in STATA
Date   Sat, 25 Aug 2012 21:42:50 -0400

Well, you should also do a parallel or Hull analysis to help determine how many non-trivial components actually exist in the data. Classical rules (e.g., Kaiser criterion)don't work very well (but haven't died yet unfortunately). 
Lorenzo-Seva, U., Timmerman, M.E., & Kiers, H.A.L. (2011). The Hull Method for Selecting the Number of Common Factors. Multivariate Behavioral Research, 46(2), 340-364.
http://psico.fcep.urv.es/utilitats/factor/Description.html
 
Timmerman, M. E., & Lorenzo-Seva, U. (2011). Dimensionality Assessment of Ordered Polytomous Items with Parallel Analysis. Psychological Methods, 16(2), 209-220.
http://www.ncbi.nlm.nih.gov/pubmed/21500916
 
Garrido, L.E., Abad, F.J., & Ponsoda, V. (2011). Performance of Velicer’s Minimum Average Partial Factor Retention Method With Categorical Variables. Educational and Psychological Measurement, 71(3), 551-570.
 
Presaghi, F., & Desimoni, M. (January 2, 2012). A Parallel Analysis With Polychoric Correlation Matrices: Package ‘random.polychor.pa’, Version 1.1.2.
http://cran.r-project.org/web/packages/random.polychor.pa/random.polychor.pa.pdf
http://cran.r-project.org/web/packages/random.polychor.pa/index.html 
Cam
----------------------------------------
> From: H.Essendi@soton.ac.uk
> To: statalist@hsphsun..harvard.edu
> Subject: st: RE: FW: Running Polychoric Principal Component Analysis in STATA
> Date: Fri, 4 Aug 012 9::8::1 +000<
>
> Hi,
>
> I have run my Polychoric PCA with 0 variables and these are my results. How do I extract the principal components?
>
>
>
> k Eigenvalues Proportion explained Cum. explained
>
> ..75133 ..29171 ..29171<
> ..14605 ..30487 ..59658<
> ..99687 ..73323 ..32981<
> ..72968 ..65766 ..98746<
> ..06116 ..60204 ..58950<
> ..91586 ..49720 ..08670<
> ..57610 ..35254 ..43924<
> ..57563 ..31919 ..75842<
> ..76737 ..29225 ..05067<
> 0 ..08630 ..26954 ..32021<
> 1 ..21940 ..24065 ..56086<
> 2 ..17829 ..20594 ..76680<
> 3 ..68042 ..18935 ..95615<
> 4 ..34358 ..17812 ..13427<
> 5 ..74645 ..15821 ..29248<
> 6 ..32420 ..14414 ..43662<
> 7 ..94679 ..13156 ..56818<
> 8 ..50109 ..11670 ..68489<
> 9 ..17694 ..10590 ..79078<
> 0 ..72341 ..09078 ..88156<
> 1 ..66147 ..08872 ..97028<
> 2 ..28569 ..07619 ..04647<
> 3 ..82232 ..06074 ..10721<
> 4 ..34601 ..04487 ..15208<
> 5 ..73532 ..02451 ..17659<
> 6 ..02814 ..00094 ..17753<
> 7 ..00000 ..00000 ..17753<
> 8 -..00000 -..00000 ..17753<
> 9 -..09973 -..00332 ..17420<
> 0 -..22612 -..17420 ..00000<
>
>
>
> scalars:
> r(lambda0)) = -.226117872285307<
> r(lambda9)) = -.099733429209876<
> r(lambda8)) = -..1788802401ee-1<
> r(lambda7)) = ..1791708536ee-1<
> r(lambda6)) = .028136759119166<
> r(lambda5)) = .735315467859793<
> r(lambda4)) = .346013978294836<
> r(lambda3)) = .822315003459927<
> r(lambda2)) = .28568953051127<
> r(lambda1)) = .661472213481918<
> r(lambda0)) = .723408357592857<
> r(lambda9)) = .176943611403527<
> r(lambda8)) = .501089523760873<
> r(lambda7)) = .946787848401978<
> r(lambda6)) = .32420025218819<
> r(lambda5)) = .746446780762609<
> r(lambda4)) = .343577888749866<
> r(lambda3)) = .680416974993906<
> r(lambda2)) = .178288336363039<
> r(lambda1)) = .219402529310105<
> r(lambda0)) = .086298902211778<
> r(lambda)) = .767365013048373<
> r(lambda)) = .575625979499038<
> r(lambda)) = ..5760970715606<
> r(lambda)) = ..91586326478875<
> r(lambda)) = ..06116092435452<
> r(lambda)) = ..72968399660107<
> r(lambda)) = ..9968656497797<
> r(lambda)) = ..14605324771372<
> r(lambda)) = ..7513321956839<
>
> Thanks,
> HIldah
>
>
>
>
> -----Original Message-----
> From: owner-statalist@hsphsun..harvard.edu [mailto:owner-statalist@hsphsun..harvard.edu] On Behalf Of Essendi H.
> Sent: 2 August 012 5::0<
> To: statalist@hsphsun..harvard.edu
> Subject: st: FW: Running Polychoric Principal Component Analysis in STATA
>
> Dear STATA,
>
> How can I run Polychoric principal component analysis in STATA? . I have likert scale data on wellbeing and I would like to prepare wealth quintiles based on these subjective responses. The challenge I am facing however is how to prepar e my variables before running this. I am not sure whether I need to recode them into dummy variables or just rung these with all the ordered category?. Also kindly advice on how to do this step by step.
>
> Many thanks,
> Hildah
>
> *
> * For searches and help try:
> * http://www.stata.com/help.cgi?search
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
>
> *
> * For searches and help try:
> * http://www.stata.com/help.cgi?search
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/ 		 	   		  
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index