To correct what I just said in my "correction" message, when individual frontrunner probabilities are judged from the win probabilities, A is 95/2 times as likely to be one of the 2 frontrunners as B is. If the win probabilities are A: .9, B:.04, C: .04, and D: .01, those don't add up to 1. Of course the sum could be more than 1 in a small election where ties are possible, but in a public election that wouldn't be so. But, using those win probabilities, and calculating for D the way I did for A, B, & C, it's D: .1 Those are just numbers estimated to be proportional to the candidates' individual frontrunner probabilities. If we multiply those numbers together for each pair, we get numbers that are estimates of numbers proportional to each pair's frontrunner probability. If we then add those up, and then divide each pair's product by that sum, we get estimates for each pair's frontrunner probability. Multiplying, for each pair, the numbers calculated for the candidates: A & B: .95 X .2 = .19 A & C: .95 X .2 = .19 A & D: .95 X .1 = .095 B & D: .2 X .1 = .02 C & D: .2 X .1 = .02 B & C: .2 X .2 = .04 These add up to .555 So the various pairs' frontrunner probabilities can be estimated by dividing that pair's product by .555 Mike Ossipoff _________________________________________________________________ Get your FREE download of MSN Explorer at http://explorer.msn.com
