Tuesday, September 25, 2007

Week 4 Predictions

The predictions are based on yards per play on rushing and passing plays (sacks and sack yards included), sack rates, third down conversion rates, penalty yards per game, and fumble and interception rates. The models are trained on the 1996-2006 seasons. Linear regression predicts the final score margin (home team points - away team points). Logistic regression estimates the probability that the home team will win.

GamePredicted Final Score MarginP(Home Team Wins)
NYJ @ BUF3.510565.9978
OAK @ MIA6.323870.3696
NE @ CIN-2.151238.6068
BAL @ CLE0.726552.6149
DEN @ IND5.487566.5365
KC @ SD3.564660.7375
STL @ DAL9.480780.1174
PHI @ NYG-0.236946.0162
CHI @ DET6.873671.3616
GB @ MIN3.711567.9140
HOU @ ATL-1.529942.1268
TB @ CAR-0.065851.4045
PIT @ ARI0.689255.9588
SEA @ SF-2.928341.3111

Week 3 accuracy numbers delayed until probably Sunday...

Addition: Here are predictions based on unadjusted stats for those who are curious

GamePredicted Final Score MarginP(Home Team Wins)
NYJ @ BUF-1.371149.0697
OAK @ MIA8.437174.1058
NE @ CIN-8.839919.1132
BAL @ CLE-0.138948.9705
DEN @ IND4.665163.2223
KC @ SD1.010753.3276
STL @ DAL13.213886.9832
PHI @ NYG-2.872638.2994
CHI @ DET8.720973.7411
GB @ MIN4.023269.0136
HOU @ ATL-0.275846.5515
TB @ CAR-3.578839.4783
PIT @ ARI-4.772437.5988
SEA @ SF-3.261740.1031

1 comment:

Brian said...

By adjusted, do you mean adjusted for past opponent strength?