Posted: Tue Jan 22, 2008 4:53 am Post subject: Basic questions about Pythagorean winning percentage
I'm hoping these are easy questions anybody here can answer. You can skip the ones that might be controversial or require opinion, as I really only need the simple stuff.
At any given point within a season, when attempting to predict subsequent games during the same season, which is better? Actual winning percentage or Pythagorean winning percentage? Are both useless for this purpose because of luck, strength of schedule, streakiness, etc.?
When looking at end-of-season records, what is the relationship between actual winning percentage and Pythagorean winning percentage? How well does the latter explain the former? When there is a large disparity between a team's actual and Pythagorean winning percentages, would we do better to attribute that difference to luck or to over/underachieving?
Is there any substantial difference when figuring Pythagorean winning percentage between using points for/against and using offensive/defensive efficiency? If so, which is better?
Posted: Tue Jan 22, 2008 10:54 pm Post subject: Re: Basic questions about Pythagorean winning percentage
Tim Lehrbach wrote:
At any given point within a season, when attempting to predict subsequent games during the same season, which is better? Actual winning percentage or Pythagorean winning percentage? Are both useless for this purpose because of luck, strength of schedule, streakiness, etc.?
The difference between the two isn't huge, but differential tends to be a better predictor after the first month or so of the season. By midseason, both have correlations of about 0.7 with the team's record in the second half of the season.
Quote:
Is there any substantial difference when figuring Pythagorean winning percentage between using points for/against and using offensive/defensive efficiency? If so, which is better?
If you're averaging team and opponent possessions and using the Pythagorean method, there is no difference. Offensive and Defensive Ratings can be a little misleading if possessions aren't equal. If you're using Expected Wins or pure point differential as opposed to the Pythagorean method, then pace can play a factor.
You cannot post new topics in this forum You cannot reply to topics in this forum You cannot edit your posts in this forum You cannot delete your posts in this forum You cannot vote in polls in this forum