For a twist on picking your basketball tournament bracket picks, read the latest paper from Sheldon Jacobson and graduate student Doug King. By studying past tournament performance using statistical tools, they find that the seedings are important, but mainly for the first two rounds. The deeper you get into the tournament, the seedings become less effective at predicting winners.
“What we are revealing statistically is something that college basketball fans probably already knew in their gut – that a team’s seeding provides some indication as to how well it is going to do, but it does not necessarily give you the definitive predictor,” Jacobson said. “In the Sweet Sixteen round, the rankings still hold, but just barely. From the Elite Eight round and onward, you might as well pick names out of a hat.”
Watch the video here.
On a related note, I wonder if twitter can enhance the tournament experience. I am going to attempt to tweet during the the tournament. Please join me to discuss the quantitative side of the tournament. I just signed up for twitter and have no idea what I am doing, so I need your expertise on this. My twitter feed is on the right side of this blog. March Madness + OR = 🙂
March 17th, 2009 at 5:46 am
Welcome to Twitter. You’re second person to join Twitter from OR community. It will be very effective and fun to tweet from tournament I think.
March 17th, 2009 at 10:55 am
[…] up on a post from Punk Rock Operations Research, let’s use a hashtag for OR people twittering about the tournament. I think […]
March 18th, 2009 at 10:45 am
Laura, you are definitely on to something here. It has definitely struck a chord.
March 18th, 2009 at 11:29 am
Excellent link, Larry. That article is so cool that it deserves its own post.
March 18th, 2009 at 1:26 pm
[…] Research as well as previous entries by me and Laura on LRMC (Logistic Regression/Markov Chain) and Laura’s article on the world of Sheldon Jackobson and Doug King. We previously saw Sheldon in articles on […]