"Mok-Kong Shen" <mok-kong.shen@t-online.de> wrote:
[snip]

I believe your assertion was that:

the two forms are simply equivalent
'representations' of the same thing
and thus shouldn't inherently affect
the statistical properties in them.

To me, this implies a claim that a reversible transform will not affect the
statistical properties of the input. My reference to AES, an example of a
reversible transform, was to demonstrate that the transform itself can
produce radical changes in the statistical properties.
[snip]