Cross Validation from PLSregress

If MSE(2,:) from PLSregress gives minimum error , how do I plot MSECV against comp num. I gave a 'cv' of 10 and ploted plsmrep against component number but seem to be underfitting. Is there any other way to do this except plot(0:compno, plsmsep(2,:),'r') if giving the 'CV' option.

Thanks, KB

Answer 1

[Abhiya]

I hope this is the way to plot MSE versus component no.

[Xl,Yl,Xs,Ys,beta,pctVar,PLSmsep] = plsregress(X,y,10,'CV',10); plot(0:10,PLSmsep(2,:),'b-o'); xlabel('Number of components'); ylabel('Estimated Mean Squared Prediction Error'); legend({'PLSR'},'location','NE');