In sci.stat.consult Elliot Cramer <[EMAIL PROTECTED]> wrote:
> In sci.stat.edu Ronald Bloom <[EMAIL PROTECTED]> wrote:

> : Suppose I have more observations than I have variables.
> : E.g. Say 51 variables and 30 observations apiece.

> : Is there anything useful I can learn nevertheless from 
> : that matrix?  
> not much;  you can't even learn much about 10 variables


  Are you saying that 30 observations on 10 variables 
is pretty much devoid of information?  Why is that?
Doesn't the sample covariance matrix on those 10 variables
tell me something about the "shape" of the cloud of 
data in 10-space?


> : E.g.:
> : Is there anything to be garnered from a principle components
> : decomposition of this covariance matrix in this circumstance?

> NO

.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
.                  http://jse.stat.ncsu.edu/                    .
=================================================================

Reply via email to