Princomp help needed to reduce-change a dimension of the matrix

I have a matrix X 400x500 (rows x column) and I use

[coeff,score,variance]=princomp(X);
%Calculate explained variance
expvar=100*variance/sum(variance);
figure; pareto(expvar);
xlabel('Number of Principal Components');
ylabel('Explained Variance %');
title('Pareto of Explained variance vs. Principal Component Number');

From this figure,I note that the first ten principal components accounts for more that 70% of the total variance

Now, how can I get my new reduced matrix using coeff,score,variance? Please help me,I'm stuck here Thank you

Answer 1

[bym]

Just use the first 10 values of coeff & score,i.e.

score(:,1:10)