how to reduce dimensionality of features by usin pca?

Now I can apply PCA in Matlab by using [coeff, score, latent, ~, explained] = pca(X);and size of X 20*20, And now my confusion begins. Should I take the first column of coeff or of score or other to get reconstructed features by pca?

Answer 1

[David J. Mack]

To get a simply answer (whitout really adressing the problem), have a look as pcares

Greetings, David