[EMAIL PROTECTED] (Alan McLean) wrote in news:9391A1A0-FAE2-
[EMAIL PROTECTED]:

> This argument relies on the symmetry of the normal and t distributions 
> - what happens with a confidence interval for a variance?
> 

Don't you need to consider the non-central T (which is not symmetric)?

The CI for the variance is determined by the appropriate percentiles of the 
(non-symmetric) chi.

David Winsemius
.
.
=================================================================
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