PCA expansion random variables

Hello everyone.

Right now I am applying PCA to a set of observations. [coeffUV, score_vectorUV, latentUV, tsquaredUV, explainedUV, muUV]=pca(Z, 'Centered',false); being Z a gaussian correlation kernel.

As far as I understand, Score columns are the eigenfunctions. I have read in some books that if one multiplies the eigenfunctions (columns of score) by the origninal matrix data, gaussian random variables are obtained. Hower, if I write randvar=Z*score(:,1); and hist(randvar) I don't get a Gaussian histogram.

Can someone tell me what I am doing wrong?

Thanks.

[Adam]

The columns of the coeff output are the eigenvectors, as explained in

doc pca