Re: Principle component analysis

[E. Joshua Rigler]

On Thu, Apr 16, 2009 at 8:54 AM, Oguz Yarimtepe <address@hidden> wrote:
> Hi,
>
> I am trying to use PCA at my project. I need to get some graphics like
> the one here[1]
>
> I am not sure how will i use octave to create such graphics after
> applying princomp funtion to my dataset. Can someone help me on this?
>
> [1] http://tinypic.com/view.php?pic=9giped&s=5
>


My guess is that the graphic you linked to is a plot of the first
column of the second output argument to princomp.m (i.e., the
"transformed data").  Either call princomp.m with a second output
argument, or multiply the demeaned input matrix by the principal
component matrix.  (e.g.,

>> pc = princomp(obs_matrix);
>> xform_matrix = center(obs_matrix)*pc;

This is exactly what princomp.m does to get the transformed data.

-EJR