Even games played with pretend money have rules and definitions of victory. After our family poker game, all the money goes back in Mommy’s coin jar, but we still know who won. * You wrote:* “After the election results are known, I will compute the Brier score for each entry. Lowest Brier score wins.”
My solution is still non-integer, and I’m “betting” on it. A single additional submission isn’t enough for me to go all-integer.
YOU are the one who wrote: “Lowest Brier score wins.” Perhaps you want to change this criterion? I pointed out the problem 8 days ago: " I’m not sure that splitting the prize money among all those tied for best score is the right approach [given Lance’s apparent objective] here."
This contest doesn’t have prize money, pretend or otherwise, but if it helps you enjoy yourself to imagine prize money then, by all means, go for it.
“Lowest Brier score wins,” does not imply that the winner takes all of the prize money that you, for some reason, are imagining, but feel free to pretend that it does if that helps motivate you. Definition of the victory condition does not imply a payout structure.
The important thing is to have fun so do whatever you need to do to have it.
If it is more enjoyable for you to maximize your chances of winning than to minimize your Brier score, then knock yourself out.
P(D):
Alabama .01
Alaska 0
Arizona (special) .8
Colorado .9
Georgia .1
Georgia (special) .5 (When your husband is a billionaire, why take a stupid chance for a measely few million?
Iowa .3
Kansas 0
Kentucky .1
Maine .8
Michigan .99
Montana .5
North Carolina .5
I barely pay attention to senate races but hey, I’ll play:
Alabama: 0.0 D
Alaska: 0.45 D
Arizona (special): 1.0 D
Colorado: 1.0 D
Georgia 0.6 D
Georgia (special) 0.55 D
Iowa 0.5 D
Kansas 0.0 D
Kentucky 0.35 D
Maine 0.95 D
Michigan 1.0 D
Montana 0.85 D
North Carolina 0.6 D
My stupid algorithm: take the best-looking candidate against the incumbent in the most recent polls shown on FiveThirtyEight, and give 50% plus 5% times each point of net delta. So for instance, Montana has Bullock at +7, and hence he gets 0.5+(0.05*7)=0.85. For the Georgia special election, I picked the candidates that seemed most promising for both parties.
Here’s my final update, and I’m glad I did. I had flipped Alabama and Alaska in my last update (alphabetical by state name is not the same alphabetical by state postal abbreviation).