[EM] Probability function for Hoffman's method

[MIKE OSSIPOFF]

I forgot to mention Hoffman's probability function for his Pij
estimating method:

He used a previous election, with the same candidates. But it could be 
identical ones, or at least the same parties.

Adjusting the candidate vote totals according to the entire vote total,
he used the outcome point of that previous election as the most
probable outcome point for the current election, the one for which
we want the Pij.

The probability density for the position of the outcome-point, at a
certain point in outcome space, is related by that point's distance
from the most probable outcome point, by the normal function.

The parameters of that normal function are chosen based on previous
elections.

He integrated that outcome-point probability density function over
the various tie regions, to determine the Pij.

Mike Ossipoff





_________________________________________________________________
Get your FREE download of MSN Explorer at http://explorer.msn.com/intl.asp.

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