[EM] Part 3, More apportionment

[Michael Ossipoff]

Concerning Ossipoff's latest "AR" ("adjusted rounding") apportionment 
method,
explained in his post titled
  "Detailed (but obvious) instructions for Adjusted-Rounding"
it sounds interesting.

To take a more abstract view of this:  it seems to me that what you can
accomplish with
the idea of treating each "cycle" on its own, is to avoid having to use ANY
probabilistic
model.

I reply:

Yes, AR & CW don't need any distribution model. They individually zero-out 
(as nearly as possible) each cycle's deviation from s/q=1.

Warren continues:

That's because the probability distribution within one "cycle," is just
the data itself.
We can now round the elements of that cycle, in such a way as to minimize 
our
favorite bias
measure.

I reply:

AR & CW both work, in different ways, to minimize each cycle's deviation 
from s/q=1.

Mike Ossipoff