20.01.2015 Views

njit-etd2003-081 - New Jersey Institute of Technology

njit-etd2003-081 - New Jersey Institute of Technology

njit-etd2003-081 - New Jersey Institute of Technology

SHOW MORE
SHOW LESS

Create successful ePaper yourself

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

291<br />

•"The Component Variances (Third Output)"<br />

•"Hotelling's T2 (Fourth Output)"<br />

The Principal Components (First Output)<br />

The first output <strong>of</strong> the princomp function, pcs, contains the 15 principal components.<br />

These are the linear combinations <strong>of</strong> the original variables that generate the new<br />

variables.<br />

6. Let's look at the first three principal component vectors.<br />

>> p3=pcs(:,1:3)<br />

P3 =<br />

0.2167 -0.1183 -0.1847<br />

0.2066 -0.1977 -0.4588<br />

0.2000 -0.2014 -0.4580<br />

-0.2819 -0.3377 0.1507<br />

-0.3001 0.1087 -0.3137<br />

-0.2786 -0.3063 -0.1575<br />

-0.2915 -0.0762 0.2091<br />

-0.2585 0.3470 0.0879<br />

-0.2663 0.3242 -0.1213<br />

-0.3025 -0.3570 0.0794<br />

-0.2793 0.1323 -0.3511<br />

-0.2737 -0.2694 -0.2520<br />

-0.2049 -0.3636 0.2074<br />

-0.2168 0.2623 -0.0036<br />

-0.2592 0.1920 -0.3122<br />

>><br />

The largest weights in the first column (first principal component) are the first and<br />

second elements, corresponding to the variables respiration and heart rate. To show the<br />

orthogonality <strong>of</strong> the principal components, note that premultiplying them by their<br />

transpose yields the identity matrix.<br />

>> I = p3'*p3

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

Saved successfully!

Ooh no, something went wrong!