2002 College Football Forecast (NCAA Div IA & IAA)

6 Jan 2002: Average model rankings (NCAA Div I & IAA) (i.e. Average model rankings from 2002)

6 Jan 2002: Current model rankings (NCAA Div I & IAA) (rank at final week of the season)

2002 Model Performance:

All Div I games               forecast probabilities
                 50-59%  60-69%  70-79%  80-89%  90-99%    100%     all
total games:        154     308     372     371     186       0    1391
number right:        83     187     271     303     182       0    1026
number expected:   85.2   198.8   283.0   315.3   170.3     0.0  1052.5
right/expected:    0.97    0.94    0.96    0.96    1.07    0.00    0.97

Breakdown by Conference and Division:
Conference games              forecast probabilities
                 50-59%  60-69%  70-79%  80-89%  90-99%    100%     all
total games:         89     191     215     217     105       0     817
number right:        43     125     152     171     102       0     593
number expected:   49.2   123.1   163.1   184.6    96.1     0.0   615.9
right/expected:    0.87    1.02    0.93    0.93    1.06    0.00    0.96

Non-Conference games          forecast probabilities
                 50-59%  60-69%  70-79%  80-89%  90-99%    100%     all
total games:         59     110     140     129      71       0     509
number right:        36      57     104     109      70       0     376
number expected:   32.7    71.0   106.9   109.2    65.1     0.0   384.9
right/expected:    1.10    0.80    0.97    1.00    1.08    0.00    0.98

Non-Division games            forecast probabilities
                 50-59%  60-69%  70-79%  80-89%  90-99%    100%     all
total games:          6       7      17      25      10       0      65
number right:         4       5      15      23      10       0      57
number expected:    3.3     4.6    13.0    21.5     9.1     0.0    51.6
right/expected:    1.20    1.08    1.16    1.07    1.10    0.00    1.11

actual/expected = 1 -- model right on
actual/expected > 1 -- model probabilities too low (more wins than expected)
actual/expected < 1 -- model probabilities too high (less wins than expected)


Please email comments or questions to bfm@BassettFootball.net