How accurate were my objective FEIN projections ? You may think that a completely automated football forecasting system won’t be as accurate as human projections such as CBS Sportsline’s , FF Today’s , or ESPN’s . Let’s see how each set of projections stacked up in accuracy for the 2009 season.
I looked at quarterbacks with 200 pass attempts, running backs with 100 rushes, wide receivers with 40 catches, and tight ends with 30 catches this season (selecting only those with a projection from each system). There were 33 QBs, 47 RBs, 54 WRs, and 25 TEs who met these criteria.
I first adjusted each system’s projections up or down to make the average projection equal to actual average of the players in the sample. (For instance, if ESPN had projected 4.5 yards per carry and the average was 4.2, I subtracted three-tenths of a yard from each player’s projection.)
Then I compared each player’s adjusted projection to his actual number. I squared the difference between the two and weighted that number based on his actual number of attempts or catches, and took the square root of the average for each system.
Here are the results.
Note: Projections were assessed on a per-attempt or per-catch basis. Projecting 1,000 rushing yards on 250 attempts is the same as projecting 400 yards on 100 attempts.
All numbers below are prorated to the average number of attempts or catches for the sample: 438 attempts for QBs; 199 rush attempts and 29 receptions for RBs; 65 receptions for WRs; and 57 receptions for TEs. The rank among the four systems is in parentheses.
| Stat | CBS | FF Today | ESPN | FEIN |
| Comp | 17.2 (2) | 17.1 (1) | 19.1 (4) | 17.5 (3) |
| Pass Yds | 366 (2) | 338 (1) | 386 (4) | 384 (3) |
| Pass TD | 5.10 (4) | 4.22 (3) | 4.16 (2) | 4.01 (1) |
| INT | 5.88 (2) | 6.26 (4) | 6.14 (3) | 5.61 (1) |
| QB FanPts | 46.8 (4) | 42.9 (2) | 44.4 (3) | 42.6 (1) |
| Rush Yds | 127 (3) | 155 (4) | 118 (1) | 121 (2) |
| Rush TD | 3.16 (1) | 3.33 (2) | 3.62 (4) | 3.36 (3) |
| RB Rec Yds | 51 (2) | 54 (3) | 63 (4) | 49 (1) |
| RB Rec TD | 1.28 (3) | 1.1 (1) | 1.60 (4) | 1.24 (2) |
| RB FanPts | 44.5 (1) | 47.5 (3) | 49.5 (4) | 44.6 (2) |
| WR Rec Yds | 123 (2) | 133 (3) | 163 (4) | 117 (1) |
| WR Rec TD | 2.29 (1) | 2.35 (2) | 2.61 (4) | 2.46 (3) |
| WR FanPts | 26.0 (1) | 27.4 (3) | 31.9 (4) | 26.4 (2) |
| TE Rec Yd | 76 (1) | 88 (3) | 97 (4) | 81 (2) |
| TE Rec TD | 2.29 (1) | 2.73 (3) | 2.73 (4) | 2.49 (2) |
| TE FanPts | 21.4 (1) | 25.2 (3) | 26.1 (4) | 23.1 (2) |
| Avg. FanPts | 34.7 (2) | 35.7 (3) | 38.0 (4) | 34.2 (1) |
CBS Sportsline won three out of the four positions, but on average, my projections were the best overall, with an average error of 34.2 fantasy points. Nevertheless, it’s only one year, and the sample size is small. But it just goes to show that objective forecasts can be as accurate as subjective forecasts.
Runner http://qpiecesba.03GMCPARTS.US/tag/Sports+Runner+vxr/ : Runner…
Runner…
Trackback by vxr — August 30, 2010 @ 1:18 am