Principal component analysis PreviousNext
Mplus Discussion > Exploratory Factor Analysis >
 Manuel posted on Thursday, June 18, 2009 - 9:46 am
is it possible to conduct a (multiple-group) principle component analysis (not factor analysis) in Mplus? If yes, where can I find information on this?
Thank you!
 Linda K. Muthen posted on Thursday, June 18, 2009 - 9:49 am
No, Mplus does not do principal component analysis.
 Manuel posted on Thursday, June 18, 2009 - 10:47 am
bad news for me;-) but thank you for your prompt reply!
 Joe posted on Friday, May 09, 2014 - 2:46 pm
Is this the reason that when I try to run the following model, I get the error: "Unknown variable(s) in an ON statement: REL"?

i s | prfsb@0 prfpm3s@1 prfpm4s@2 prfsm@3 prfpm7s@4 prfpm8s@5 prfpm9s@6 prfse@8;

rel ON prfsb prfpm3s prfpm4s prfsm prfpm7s prfpm8s prfpm9s prfse;
 Linda K. Muthen posted on Friday, May 09, 2014 - 4:02 pm
I would need to see the full output and your license number at to know why you get this message. It has nothing to do with principal component analysis.
 Calvin D. Croy posted on Monday, April 25, 2016 - 10:32 am
Linda, in 2009 your responded to a question by saying that Mplus does not do Principal Components Analysis. Is that still true?

I didn't see it mentioned in the Mplus 7.0 Users guide.

By principal components analysis I mean extraction of orthogonal components that are weighted combinations of observed values. The components explain 100% of the observed variance, and one can say how much variance is accounted for by each component.

If Mplus does do Principal Components Analysis now, could you point me to the Mplus syntax?

Thank you very much.
 Linda K. Muthen posted on Monday, April 25, 2016 - 11:18 am
Yes, this is still true. Mplus does not do Principal Component Analysis.
 Jan Ivanouw posted on Monday, October 16, 2017 - 1:46 pm

While I am not advocating the use of Principal Conponents analysis, some psychological research rely heavily on this method. In order to estimate the amount of error stemming from this method, I would like to examine some data sets with both PC and EFA.
Now, I wonder if I can mimick PC by fixing residual variance to 0, forcing all variance to be used in the definition of the factors?
 Bengt O. Muthen posted on Monday, October 16, 2017 - 4:23 pm
Maybe that works, keeping the factors uncorrelated. But I wonder if those zero residual variances will lead to a non-pos def covariance matrix.
 Jan Ivanouw posted on Tuesday, October 17, 2017 - 11:15 am
Hi Bengt,

Thank you for you answer.

I tried with a CFA.
You're right about the covariance matrix. However, it works when I fix the residual variances at a very small amount.

Is it possible to try out the same with EFA or ESEM. I tried, but
- for EFA it seems that I cannot fix error variance,
- for ESEM I could not get it to accept specification either of orthogonal factors or fixed error variances.

Did I just not do it right, or is it impossible in Mplus? How would the commands look like?
 Bengt O. Muthen posted on Tuesday, October 17, 2017 - 6:17 pm
I think you can do it in ESEM by choosing the right rotation procedure and by fixing residual variances to low values. But on the whole, I'm not sure it is worth trying out and instead just do PCA by other software.
 Jan Ivanouw posted on Wednesday, October 18, 2017 - 4:48 am
I agree
Thank you
Back to top
Add Your Message Here
Username: Posting Information:
This is a private posting area. Only registered users and moderators may post messages here.
Options: Enable HTML code in message
Automatically activate URLs in message