Re: Can I use rank data to do PCA?

[Rich Ulrich]

On 28 May 2000 17:25:18 GMT, [EMAIL PROTECTED] (Wen-Feng
Hsiao) wrote:

 Dear Ulrich,
 
 Thanks for your reply. I now have more confidence in analyzing my data
 with PCA. However, you mentioned that 43 subjects are too thin to obtain
 a stable/converge result. This incurs me another question -- how many
 subjects are enough to obtain a stable result, if the same set of
 stimuli are rated by a 5-point scale? 50? (supposed that each rating 
 point needs 10 subjects.)
 ...
The rule-of-thumb is 10 subjects per variable, and that is assuming
the sort of correlations and structure common in clinical research and
many other places.  With dichotomous measures, you might need more,
since the correlations are attenuated.  With unambiguous structure,
you would need less.

-- 
Rich Ulrich, [EMAIL PROTECTED]
http://www.pitt.edu/~wpilib/index.html


===
This list is open to everyone.  Occasionally, less thoughtful
people send inappropriate messages.  Please DO NOT COMPLAIN TO
THE POSTMASTER about these messages because the postmaster has no
way of controlling them, and excessive complaints will result in
termination of the list.

For information about this list, including information about the
problem of inappropriate messages and information about how to
unsubscribe, please see the web page at
http://jse.stat.ncsu.edu/
===

Can I use rank data to do PCA?

[Wen-Feng Hsiao]

Dear listers,

I have 43 subjects to rank 11 stimuli. To obtain the underlying 
variables, principal components, I conduct a PCA (Principal Component 
Analysis) to the obtained ranked-data. However, a friend of mine told me 
that using ranking data to do a PCA is quite dangerous, since the scores 
for the 17 stimuli from each subject is not independent. (I.e. the last 
stimulus always score 17 if we know the first 16 stimuli.) I am not sure 
whether it is right or wrong. Any suggestion?

Wen-Feng


===
This list is open to everyone.  Occasionally, less thoughtful
people send inappropriate messages.  Please DO NOT COMPLAIN TO
THE POSTMASTER about these messages because the postmaster has no
way of controlling them, and excessive complaints will result in
termination of the list.

For information about this list, including information about the
problem of inappropriate messages and information about how to
unsubscribe, please see the web page at
http://jse.stat.ncsu.edu/
===