student
Joined: 19 May 2007 Posts: 1
|
Posted: Wed May 23, 2007 10:39 pm Post subject: Kalman Formulas |
|
|
I was trying to make predictions of wnba games by this method (it's great fun to me lol): http://www.rawbw.com/~deano/articles/kalman.html
The author mentioned that the rating of two teams should be adjusted based on their actual performance according to
http://www.rawbw.com/~deano/articles/kalman/formula.html
I've been trying to predict wnba games using his method but I don't know how to update team rating based on actual performance, please help. (I'm completely lost when I read the sentences in bold below)
"Using a prior variance of 20 for both Chicago's ratings and the Celtics' ratings, the variance of the expected ratings is about 40[=(20*20 +109.82*20+104.82*20)/(106.12) for the offense, = (20*20 +104.22*20+107.72*20)/(106.12) for the defense]. In general, ratings fluctuate from game to game with a standard deviation of 12 (or a variance of 150) . Hence, the Kalman weight is 0.2145 [=41/(41+150)]. The updated road offensive rating for the Bulls is then 107.9 [=109.8+0.2145*(99.8-108.5)]. The variance on this new estimate is 15.7 [=(1-0.2145)*20], only a slight drop from before. For the defense, the updated rating is 104.8 [=105.2+0.2145*(105.0-105.2)], a slight improvement. The variance decreased to 15.8."
For example, if team A has an OR of 100 and DR of 95, and team B has a OR of 102 and DR of 100, with a league average rating of 100, how will team A OR change if they win by 99-90 with 95 possessions (assuming neutral court)? |
|