[EM] Modeling elections

[Richard Moore]

Richard Moore wrote:
> I just did a short run -- 5 candidates, 49 possible positions in a 2-D
> issue space, 50 tests:

One more correction -- it was 961 possible positions (ranging from -15 
to +15
in each dimension, so 31*31).

Incidentally, to get some feel for multimodal distributions, I populated
the voter field with three rectangular areas -- one covering the full
issue space, and two smaller 7x7 regions superimposed in opposing quadrants,
with 300, 260, and 240 voters randomly but uniformly distributed in each
rectangle.

  -- Richard

----
For more information about this list (subscribe, unsubscribe, FAQ, etc), 
please see http://www.eskimo.com/~robla/em