why compression doesn't perfectly even out entropy

[David Wagner]

In article <199604182255.PAA13373 at jobe.shell.portal.com>,
Hal  <hfinney at shell.portal.com> wrote:
> So I think the lesson is that there is only one way to estimate entropy,
> and that is to study your source.  I have to agree with Perry that this
> filtering concept is not the way to go.  It is a red herring that lures
> you in the direction of automatic entropy estimation, and that is really
> not safe.

Excellent point!  Very nicely put.

You've convinced me: I was looking at the problem the wrong way.
Thanks for correcting & educating me...

Appreciative of the "signal",
-- Dave Wagner