Please visit Puckerings for more hockey stuff by me   

The NHL season is finally over, so we can see now how my 2002/03 predictions stacked up to The Hockey News. Little has changed since the last update, with both predictions for the East worsening and both predictions for the West improving, by small amounts.

To evaluate the predictions, I will use the coefficients of correlation between the predicted conference rankings and the actual conference rankings (based on total points), for the final 2002/03 NHL standings. Really good predictions will have high positive correlation coefficients, say around 0.70 or higher. So without further ado, here are the results:

Take that, self-proclaimed “Bible of Hockey”! Losing to a mere mortal such as myself! Maybe I should ask for a job.

San Jose’s puzzling disintegration is the single largest reason for the low coefficients in the West, along with Minnesota’s performance. In the East things went mostly as expected, with only Tampa being a real surprise, as well as Carolina (who The Hockey News had at 7th but I had at 10th).

This was certainly a fun experiment. I may try it again next year, to see if my victory was a fluke, or if I’m actually a better predictor than a certain widely-read publication. Until then, I leave it for you to decide.