June 1, 2011

Two months in, a Bayesian look at the standings

At the end of April, I posted "Early season standings and Bayes" that took two different approaches to regressing the early season standings to come up with a prediction for the eventual result for the full season.

So here we are at the end of May, and there's been a lot of movement in the standings, so here's an update to the spreadsheet. Although the Phillies and the Indians remain at the top of the standings, they are starting to regress downwards. At the end of April, both teams were "on pace" to win 112 games in the season, but the regression showed a more modest result of 93 wins. A month later both teams are "on pace" to win 100, but the Bayesian approach suggests that they are more likely to win 91 games.

If you are a Twins or an Astros fan, there is no solace in the fact that both teams have not regressed toward the mean over the past month, but have instead continued to play at roughly the same level they exhibited in April. The regression model now predicts the Twins will end up at 65 wins, which would be the lowest in MLB. Of course, this prediction is based only on the team's performance to date -- it doesn't consider the number of injuries the Twins are currently dealing with.


No comments:

Post a Comment

Note: Only a member of this blog may post a comment.