Statistical Baseball Predictions

As the 2012 Major League Baseball season gets under way, it’s a good time to check in on the predictions of Bruce Bukiet, mathematics professor at the New Jersey Institute of Technology.

http://m.njit.edu/~bukiet/baseball/baseball.html

Using the performance data from all of the expected players, Bukiet applies a mathematical model to predict the final win-loss standings for every team in the league.  Last year, Bukiet’s model correctly identified six of the eight playoff teams.

Unlike most predictors (my statistics friends would probably prefer I use the term projectors), Bukiet does not seem shy about comparing his past predictions to the actual results.

An interesting mathematical question would be “How can we measure how accurate these predictions really are?”