Saturday, December 10, 2016

Guess the Lines - Week 15

Here are the week 14 results and week 15 predictions for this installment of "Guess the Lines". This is a weekly feature in which I put my Vegas NFL rankings to the test by predicting the point spread of upcoming NFL games. I compare the accuracy of my prediction against those of Bill Simmons and Cousin Sal, as featured on their weekly NFL podcast. In addition, I also calculate an implied point spread from ESPN Chalk's weekly Vegas NFL rankings.

Here are the week 14 results. Bill Simmons wins for the second week in a row, with a mean absolute error of 1.00 points.

Week 14 Resultspredicted point spread:
gameaGPFhGPFmeespnbillsalactual
OAK @ KC 2.6 3.1 -3.0 -1.5 -3.5 -4.0 -3.5
PIT @ BUF 4.4 1.3 +0.5 0.0 +2.0 +2.5 +2.0
CIN @ CLE -0.9 -9.1 +5.5 +6.5 +5.0 +7.0 +4.5
NO @ TB 2.2 -0.7 +0.5 -1.5 -3.0 -3.0 -2.5
HOU @ IND -2.6 -2.7 -2.5 -1.5 -3.0 -3.5 -4.5
ARZ @ MIA 1.2 -1.3 0.0 -1.0 -2.5 -4.0 -2.5
WAS @ PHI 1.2 2.6 -4.0 -2.0 +2.0 +1.5 +1.0
NYJ @ SF -4.9 -7.1 -0.5 +2.5 +2.5 +3.5 0.0
DAL @ NYG 5.0 0.7 +2.0 +2.0 +3.0 +1.0 +3.0
MIN @ JAC 0.2 -4.4 +2.0 +4.5 +4.0 +4.5 +3.0
CHI @ DET -6.6 -0.7 -8.5 -6.5 -10.0 -7.0 -8.0
SEA @ GB 5.1 0.1 +2.5 -0.5 +1.5 0.0 +2.5
SD @ CAR 1.0 1.7 -3.0 -1.5 -3.0 -6.0 -3.0
ATL @ LA 4.2 -4.1 +6.0 +6.5 +6.0 +4.5 +5.5
DEN @ TEN 3.2 -1.2 +2.0 +1.5 +3.0 +3.0 -1.5
BAL @ NE -0.2 6.8 -9.5 -8.5 -6.5 -7.0 -7.5
Mean Absolute Error 1.53 1.91 1.00 1.66

The closest prediction for each game is shown in bold. As a reminder, my predictions and the ESPN predictions were made a week ago Tuesday, so as not to be influenced by the week 14 opening lines.

Here is a summary of the weekly results. A lower score is better (we are measuring average prediction error). After holding the overall lead for the first four weeks, I drop to second behind Bill. Cousin Sal is not too far behind, and the ESPN Chalk rankings are a distant fourth.

Mean Absolute Prediction Error:
week me espn bill sal
10 1.29 1.86 1.89 1.68
11 1.11 1.46 1.29 1.07
12 1.38 1.75 1.28 1.22
13 1.13 1.70 0.87 1.10
14 1.53 1.91 1.00 1.66
average 1.29 1.74 1.27 1.35

Inspired by a suggestion in the comments in the week 12 post, I have also summarized how well each participant predicted the actual margin of the game:

Mean Absolute Prediction Error (actual margin):
week me espn bill sal vegas
10 9.32 9.61 8.79 8.64 9.54
11 5.25 5.25 4.14 3.93 4.57
12 8.44 8.69 8.16 7.59 7.50
13 12.43 12.33 13.10 12.73 12.77
average 8.86 8.97 8.55 8.22 8.59

Over four weeks, both Bill and Cousin Sal have done a better job than Vegas at predicting actual results. For reference, over the long term the average miss in the Vegas line is about 10 points. Note how week 13 was a particularly surprising week when it comes to scoring margins.

Week 15 Predictions

Here are the week 15 predictions for both my model (based on the Tuesday version of my Vegas rankings), as well as the December 6 rankings from ESPN Chalk. I forgot to tweet these on Tuesday, so you'll just have to trust me that these are based on the December 6 version of my NFL rankings. The rankings as of today already reflect week 15 opening lines.

Week 15 Predictionspoint spread
gameaGPFhGPFmeespnbillsalactual
CLE @ BUF -8.3 0.8 -11.5 -11.5
TB @ DAL -0.2 5.6 -8.5 -7.0
IND @ MIN -0.6 0.9 -4.0 -4.5
MIA @ NYJ -1.8 -5.8 +1.5 +1.0
PHI @ BAL 0.1 2.0 -4.5 -4.0
SF @ ATL -7.7 3.6 -14.0 -15.0
JAC @ HOU -4.8 -3.5 -4.0 -7.5
DET @ NYG -0.1 0.4 -3.0 -2.5
GB @ CHI 0.9 -5.5 +4.0 +5.5
CAR @ WAS -0.5 1.8 -5.0 -4.0
NE @ DEN 6.7 2.4 +2.0 0.0
OAK @ SD 2.5 0.7 -0.5 +0.5
LA @ SEA -5.0 5.7 -13.0 -13.0
NO @ ARZ 0.3 0.6 -3.0 -5.0
PIT @ CIN 5.3 0.8 +2.0 +0.5
TEN @ KC 0.0 2.9 -5.5 -5.5

No comments:

Post a Comment