rotated scores after varimax rotation

Dear all,

I'd like to verify if my approach is right. I'd like to obtain rotated subject scores after varimax rotation.

I have matrix M and perform pca:

[coeff, scores, latent, tsquared explained] = pca(M);

Then I rotate the first two PCs:

[RotatedCoeff,RotMatrix] = rotatefactors(coeff(:,1:2));

And compute rotated subject scores:

RotatedScores = scores(:,1:2)*RotMatrix;

Is this the right way to obtain rotated scores?

Thanks,

Best

Hans

Answer 1

[Umang Pandey]

Hi Hans.

Your approach is correct. By rotating the coefficients and then applying the rotation matrix to the scores, you are effectively obtaining the rotated subject scores. This allows you to interpret the components in the context of the rotated factor loadings.

You can refer to the following MATLAB documentation on "rotatefactors" for more information on parameters involved:

https://www.mathworks.com/help/stats/rotatefactors.html

Best,

Umang

Answer 2

[Hans van der Horn]

Thanks Umang!