How well all six models matched the 2009-10 final coaches' poll.
Table explanation: The Spearman Correlation Coefficients (SCC) below relate to how well the top 15, 25 and 35 teams, in the final coaches' poll, match with the predictions for the models listed. The '0,1,2' column contains how many top 35 team rankings were only off by 0, 1, or 2 places, and this is followed by the average deviation between the actual ranking and the prediction. ("X" in the large table at the bottom represents the number of wins in the NIT tournament that a team earned.)
SCC15 | SCC25 | SCC35 | 0,1,2 | Average | |
ZP2 | 0.92143 | 0.92808 | 0.96190 | 9,8,4 | 2.0000 |
PR2 | 0.92679 | 0.93923 | 0.96443 | 11,6,6 | 1.8857 |
50T | 0.92679 | 0.93385 | 0.96373 | 10,8,5 | 1.9706 |
LN2 | 0.79821 | 0.90885 | 0.94594 | 8,9,7 | 2.2059 |
ZPF | 0.67857 | 0.86615 | 0.91569 | 4,7,8 | 3.1176 |
MCB | 0.90536 | 0.88077 | 0.91199 | 7,6,1 | 3.1765 |
OCC | 0.92321 | 0.95942 | 0.92234 | 7,13,6 | 2.0857 |
Commentary: The PR2, 50T, and ZP2 models were the most consistently accurate ones, across all three sets (the top 15, 25 and 35 teams) this year, and only #18 Maryland (predicted as the #24 or #25 team) had a predicted final poll value that differed by more than 5 with the final coaches' top 25 teams - with regards to these three models. (MCB did predict Maryland in the 18th spot, but it also had the highest average difference, of all six models, across the entire range of top 35 teams.) The LN2 and ZPF models had significantly more trouble accurately predicting where #14 Xavier would be ranked, which is why those model's SCC-15 values were significantly lower (than those values accrued by the other four models), though both less accurate models (along with MCB) were much closer (to PR2, 50T, and ZP2) with regards to their SCC-25 and SCC-35 values. The SCC-35 value for the 50T model was the fourth highest it has achieved, and the value for the MCB model (for this, same comparison metric) was its fifth highest recorded quantity since this final poll was 'reinstated' in 1993. The SCC-15 and SCC-25 values for the ZPF model are the lowest ever, heavily influenced by Xavier (as mentioned above). #27 Temple, who was ranked as the #16 team by the ZPF approach, hindered ZPF's SCC-35 value as well. (Four exact matches is the second smallest value in that category for ZPF, and its average difference was the second highest its ever been - and well below the largest SCC-35 value for this model (3.8), which was tabulated for the 1994-95 season.)
The MCB model, which is heavily influenced by a team's Power rating, and winning percentage, matched Kansas' final rank (#6) better than the other models which are influence more significantly by a team's NCAA tournament performance. These seven models couldn't agree where NIT champion Dayton should be ranked: the Flyers were voted as the #33 team, and three models had them as the #28 team, ZP2 was only off my one position (#32), OCC had them as #31, and the other two models ranked Dayton three and four positions lower than #33. Only 34 teams received votes this year: Dayton received 3 votes, with the #32 team garnering 5, and the #34 team collecting just one.
TeamName | Poll | Wins | ZP2 | PR2 | 50T | LN2 | ZPF | MCB | OCC |
Duke | 1 | 6 | 1 | 1 | 1 | 1 | 1 | 1 | 1 |
Butler | 2 | 5 | 2 | 2 | 2 | 2 | 2 | 2 | 2 |
WestVirginia | 3 | 4 | 3 | 3 | 3 | 3 | 3 | 4 | 3 |
MichiganSt | 4 | 4 | 5 | 4 | 4 | 4 | 5 | 7 | 5 |
Kentucky | 5 | 3 | 4 | 5 | 5 | 5 | 4 | 3 | 4 |
Kansas | 6 | 1 | 10 | 11 | 11 | 10 | 9 | 5 | 7 |
KansasSt | 7 | 3 | 6 | 6 | 6 | 6 | 6 | 6 | 6 |
Syracuse | 8 | 2 | 7 | 8 | 8 | 7 | 7 | 8 | 8 |
Tennessee | 9 | 3 | 9 | 7 | 7 | 8 | 10 | 10 | 10 |
Baylor | 10 | 3 | 11 | 9 | 9 | 11 | 12 | 9 | 11 |
OhioSt | 11 | 2 | 8 | 10 | 10 | 9 | 8 | 11 | 9 |
Purdue | 12 | 2 | 12 | 12 | 12 | 12 | 11 | 12 | 12 |
NorthernIowa | 13 | 2 | 15 | 15 | 15 | 15 | 15 | 16 | 15 |
Xavier | 14 | 2 | 17 | 16 | 16 | 23 | 26 | 15 | 19 |
Villanova | 15 | 1 | 14 | 14 | 14 | 13 | 13 | 20 | 13 |
NewMexico | 16 | 1 | 13 | 13 | 13 | 14 | 14 | 22 | 14 |
Cornell | 17 | 2 | 22 | 22 | 22 | 20 | 24 | 21 | 17 |
Maryland | 18 | 1 | 25 | 24 | 25 | 26 | 23 | 18 | 24 |
StMary'sCA | 19 | 2 | 19 | 18 | 18 | 16 | 22 | 14 | 16 |
Pittsburgh | 20 | 1 | 18 | 19 | 19 | 18 | 18 | 27 | 21 |
Washington | 21 | 2 | 21 | 21 | 21 | 22 | 25 | 17 | 18 |
BYU | 22 | 1 | 16 | 17 | 17 | 17 | 17 | 13 | 20 |
Gonzaga | 23 | 1 | 23 | 23 | 24 | 21 | 19 | 26 | 22 |
Wisconsin | 24 | 1 | 20 | 20 | 20 | 24 | 20 | 19 | 23 |
TexasA&M | 25 | 1 | 27 | 27 | 27 | 27 | 27 | 25 | 25 |
Georgetown | 26 | 0 | 26 | 26 | 26 | 25 | 21 | 34 | 27 |
Temple | 27 | 0 | 24 | 25 | 23 | 19 | 16 | 31 | 26 |
GeorgiaTech | 28 | 1 | 30 | 31 | 32 | 29 | 30 | 32 | 29 |
Vanderbilt | 29 | 0 | 35 | 35 | 31 | 35 | 36 | 33 | 30 |
California | 30 | 1 | 29 | 30 | 30 | 31 | 32 | 23 | 39 |
MurraySt | 31 | 1 | 34 | 34 | 35 | 30 | 31 | 28 | 41 |
Missouri | 32 | 1 | 28 | 29 | 29 | 32 | 33 | 24 | 38 |
Dayton | 33 | "5" | 32 | 28 | 28 | 36 | 28 | 37 | 31 |
OldDominion | 34 | 1 | 31 | 32 | 33 | 28 | 29 | 30 | 28 |