01.03.2013 Views

Applied Statistics Using SPSS, STATISTICA, MATLAB and R

Applied Statistics Using SPSS, STATISTICA, MATLAB and R

Applied Statistics Using SPSS, STATISTICA, MATLAB and R

SHOW MORE
SHOW LESS

Create successful ePaper yourself

Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.

8.3 Principal Components of Correlation Matrices 343<br />

variables as well as the data groups that best reflect the behaviour of those<br />

variables.<br />

Figure 8.7. Dimensionality reduction of the first two classes of cork-stoppers:<br />

a) Eigenvalues; b) Principal component scatter plot (compare with Figure 6.5).<br />

(Both graphs obtained with <strong>STATISTICA</strong>.)<br />

Consider the means of variable F1 in Example 8.6: 0.71 for class 1 <strong>and</strong> −0.71<br />

for class 2 (see Figure 8.7b). As expected, given the translation y = x – x , the<br />

means are symmetrically located around F1 = 0. Moreover, by visual inspection,<br />

we see that the class 1 cases cluster on a high F1 region <strong>and</strong> class 2 cases cluster on<br />

a low F1 region. Notice that since the scatter plot 8.7b uses the projections of the<br />

st<strong>and</strong>ardised data onto the F1-F2 plane, the cases tend to cluster around the (1, 1)<br />

<strong>and</strong> (−1, −1) points in this plane.<br />

Figure 8.8. Factor loadings table (a) with significant correlations in bold <strong>and</strong> graph<br />

(b) for the first two classes of cork-stoppers, obtained with <strong>STATISTICA</strong>.

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!