Welcome to the 7th NFL PT Awards. The purpose of these
awards is to help raise the publicity for those systems that
have been superior in various qualities of interest.
Most awards will be based entirely on the numbers I've
monitored with my prediction tracker web pages. In 2006 the
number of NFL systems grew to 57, up 5 from last year.

BEST STRAIGHT UP WINNERS (Entire Season)

Winner: Least absolute value regression

Least Absolute value regression (L1) claims the crown of most wins in the
full season for the second time in three years. L1 had a record of 167-100,
62.55% By far the lowest total to ever win the season. For comparison the
Line won the previous year with a record of 193-74, 26 games better than the
winner this season, which is the current record. And L1 won by a fairly wide
margin of 4 games. Least Squares regression and Stephen Kerns tied for second.
So overall this was a terrible year for computer ratings predicting winners.

2006 Winner: Least Absolute Value Regression
2005 Winner: Vegas Line
2004 Winner: Least Absolute Value Regression
2003 Winner: Beck Elo
2002 Winner: Herman Matthews
2001 Winner: JFM Power Ratings, ARGH Power Ratings
2000 Winner: CPA Rankings
1999 Winner: Kenneth Massey Ratings

BEST AGAINST THE SPREAD (Entire Season)

Winner: Brian Gabrielle

Interestingly enought, the winner of the best against the spread award goes to
the ratings of a professional gambler, Brian Gabrielle. His ratings had a record
of 154-107, 59%. That is extremely good considering this is for every game and not
just select games. This breaks the previous record of 57.5% set in 2004.
This year about 70% of the systems finished with records better than 50%. A year
ago only 10 did better than 50%. The year before that only 5 did worse than 50%.
So there are definitely cycles. I know that last year the sportsbooks had a miserable
year because so many favorites were winning. Perhaps this year there was an over-adjustment
that lead to a lot of favorites losing (the line was less than 60% straight up).
Ed Kambour and Tom Benson also had strong years winning 55%.

Winner 2006: Brian Gabrielle
Winner 2005: Least squares with team HFA
Winner 2004: Least Absolute Value Regression
winner 2003: CPA Retro Rankings
winner 2002: FreeSportsPlay.com
winner 2001: CPA Rankings
winner 2000: Yourlinx
winner 1999: PerformanZ Ratings

SMALLEST MEAN ABSOLUTE ERROR (Entire Season)

Winner: Brian Gabrielle

As mentioned above the line did not have a typically strong season this year
and for only the second time does not win this award. This year the award goes
to Brian Gabrielle with a average error of 10.7324. Jon Dokter actually had
a lower value of 10.726 but did not have predictions for week 1. In an attempt
to see if he deserved the award I through out the first week for everyone but when
I did that he was no longer the leader. That was Gabrielle.
These numbers are quite a bit off last years winning mark and record of 9.95
The computer adjusted line, line, and opening line followed behind Gabrielle and
Dokter.

Winner 2006: Brian Gabrielle
Winner 2005: Vegas Line
Winner 2004: Vegas Line
winner 2003: Vegas Line
winner 2002: FreeSportsPlay.com
winner 2001: Vegas Line
winner 2000: Vegas Line
winner 1999: Vegas Line

SMALLEST BIAS (Entire Season)

Winner: Tom Benson

It was a strange year for bias. Only one system out of 57 had a negative bias
and that was our winner Tom Benson. His average bias was -0.1485. On average
these were running aroudn +2 or even higher. Only six systems were even under 1.
It wasn't just that the underdogs were winning this season it was the road
underdogs.

Winner 2006: Tom Benson
Winner 2005: Sagarin Elo
Winner 2004: System Average
winner 2003: CPA Rankings
winner 2002: Sagarin Pure Points
winner 2001: ARGH Power Ratings
winner 2000: Pigskin Index
winner 1999: Flyman Ratings

MOST ACCURATE SYSTEM - SMALLEST MEAN SQUARE ERROR (Entire Season)

Winner: Computer Adjusted Line

The Vegas line gets totally shut out of the full season awards this season.
My computer adjusted line earns the award of most accurate system with
a mean square error of 181.102. The line did come in second. This is
a good deal below the record of 166.808 set in 2004. Quite a few systems
were relatively close this year. Dokter, Covers, Ashly and Trexler were
all closer to the lead than the computer systems usually are.

Winner 2006: Computer Adjusted Line
Winner 2005: Vegas Line
Winner 2004: Vegas Line
winner 2003: Vegas Line (Opening)
winner 2002: FreeSportsPlay.com
winner 2001: Vegas Line
winner 2000: Pigskin Index

SECOND HALF AWARDS

I like to look at the results over the second half of the season. The
systems have had time to become 'burned in' to the season's data and
there is less reliance on starting values or previous seasons.
Second half data consists of all games from week 10 through the superbowl.

BEST STRAIGHT UP WINNERS (Second Half)

Winner: Least absolute value regression

This category has a history of having multiple winners per year but this
year Least absolute value regression finishes on top alone. Least squares
regression was second, two games back. The next two systems were 4 games behind.
And it is not like L1 ran away with it, it had a record of only 88-51, 63.31%.
It was just a bad season picking winners. The leaders of 2005 share the record
of 72.99%

Winner 2006: Least absolute value regression
Winner 2005: Vegas Line, Nutshell Sports
Winner 2004: Pigskin Index
Winner 2003: JFM Power Ratings, Kasulis Enhanced Spread, Beck Elo
Winner 2002: Least absolute value regression, JFM Power Ratings, CPA Rankings
Winner 2001: Pythagorean Ratings, Elo Ratings, Ken Massey Ratings
Winner 2000: PerformanZ Ratings, Scoring Effeciency
Winner 1999: Ken Massey, Ed Kambor, Pythagorean Ratings

BEST AGAINST THE SPREAD (Second Half)

Winner: CPA Rankings, Steve Wrathell

The best record against the spread in the second half was seen in CPA Rankings,
81-57, 58.27%. That really isn't too much behind the leaders straight up. In fact
CPA had the same record against the spread as straight up. That has got to be
unusual. It is also interesting that Gabreille did so well for the full season,
59%, but only 55.5% over the second half, so he had to have started off extremely
well and faded as the season progessed. The numbers in general were lower for the
second half than they were for the full season. As is often the case, the real
winner is an anti-winner, Nutshell sports was only 39%. So you best best would have
been to play opposite of those his picks.

Winner 2006: CPA Rankings
Winner 2005: Tom Benson
Winner 2004: ARGH Power Ratings
Winner 2003: Logistic Regression, Viacheslav Ugolnikov
Winner 2002: Least absolute value regression
Winner 2001: Stat Fox
Winner 2000: Pythagorean Ratings
Winner 1999: Least squares using team specific home field advantages

SMALLEST MEAN ABSOLUTE ERROR (Second Half)

Winner: Jeff Self

Vegas wins this category every other year. Since they won last year it was someone else's
turn this year. That would be Jeff Self, whose mean error of 10.7803 beats the line by
only 0.0003 points. Three or four others were within about 0.01 points. Again, this
is quite a ways off the record of 9.9489 set in 2005.

Winner 2006: Jeff Self
Winner 2005: Vegas Line
Winner 2004: Least Squares Regression
Winner 2003: Vegas Line
Winner 2002: FreeSportsPlays.com
Winner 2001: Vegas Line
Winner 2000: Pythagorean Ratings

SMALLEST BIAS (Second Half)

Winner: CPA Retro Rankings, Steve Wrathell

The average biases were huge for the second half of the season. On average they were running greater than
3 points in favor of the home team. Only three systems had a bias of less than 2 points. The lowest
of which was CPA Retro Rankings 1.71993.

Winner 2006: CPA Retro
Winner 2005: Kasulis Enhanced Spread
Winner 2004: Tom Benson Gridmarks
Winner 2003: CPA Rankings
Winner 2002: StatFox.com
Winner 2001: Monte Carlo Markov Chain
Winner 2000: Flyman Performance Ratings
Winner 1999: Flyman Performance Ratings

MOST ACCURATE SYSTEM - SMALLEST MEAN SQUARE ERROR (Second Half)

Winner: CPA Rankings, Steve Wrathell

This has been an interesting category because you would expect the line to
win but it has only one once over the seven years. And because we have never
had a repeat winner. This year's winner is CPA Rankings with a mean square
error of 170.103. This was almost identical to the winning MSE last season.
We have to go all the way back to the first year, 2000, to find the record
of 165.954 by the Pythagorean ratings.

Winner 2006: CPA Rankings
Winner 2005: Vegas Line
Winner 2004: Computer Adjusted Line
Winner 2003: Viacheslav Ugolnikov
Winner 2002: FreeSportsPlay.com
Winner 2001: Hank's Power Ratings
Winner 2000: Pythagorean Ratings

BEST PREDICTIVE SYSTEM (Entire Season)

Winner: Brian Gabrielle

For best overall awards I gave points to a system in each
category based on how well they do. I then sum the points. Hopefully this
gives an accurate read on who is the best system across the board.
This year it was a close race between the top two but the best
predictive system for 2006 goes to Brian Gabrielle. Second place was
the computer adjusted line.

Winner 2006: Brian Gabrielle
Winner 2005: Vegas Line
Winner 2004: Least Absolute Value Regression
Winner 2003: Beck Elo
Winner 2002: Matthews Grid
Winner 2001: CPA Rankings
Winner 2000: Ed Kambour

BEST PREDICTIVE SYSTEM (Second Half)

Winner: CPA Retro Rankings, Steve Wrathell

CPA Rankings won two individual awards for the second half but it is CPA Retro that
wins the overall prize of best predictive system during the second half of 2006.
CPA Rankings finished in second. CPA Retro was able to pull adead because of
a significantly better win/loss record.
For seven years now we have never had a repeat winner for best predictive
system for either the full season or second half.

Winner 2006: CPA Retro
Winner 2005: Hank Trexler
Winner 2004: ARGH Power Ratings
Winner 2003: CPA Rankings
Winner 2002: Kenneth Massey
Winner 2001: Monte Carlo Markov Chain
WInner 2000: Pythagorean Ratings

RETRO AWARDS

The retrodictive categories are based on each systems final
standings and measure things by applying those final ratings
to the entire season in retrospect.

As I did in the college awards I am going to break this down
into big systems (estimate team specific home field advantage)
and simple systems (do not estimate team specific home field advantage).

MOST RETRODICTIVE WINS - Large System

Winner: The Sports Report

The Sports Report SLOTS system has become well established as the system to
retroactively predict the winners of the season. SLOTS wins for the 5th
time in a row with a record of 221-44, 83.4%. This is well of the record
of 89.85% that it set last season. The Sports Report's Elo ratings was
the closest competitor, 19 games behind.

Winner 2006: The Sports Report SLOTS
Winner 2005: The Sports Report SLOTS
Winner 2004: The Sports Report SLOTS
Winner 2003: The Sports Report SLOTS
Winner 2002: The Sports Report SLOTS
Winner 2001: The system average
Winner 2000: CPA Rankings

MOST RETRODICTIVE WINS - Simple Ssystem

Winner: Jeff Sagarin

The best retrodiction record for those not fitting a team home field
advantage came from Jeff Sagarin, 195-72, 73%. The record was 78% set by
Dunkel Index last year. Over the last four years we have had four different
winners.

Winner 2006: Jeff Sagarin
Winner 2005: Dunkel Index
Winner 2004: Brian Gabrielle
Winner 2003: Frank Alder

SMALLEST RETRODICTIVE ABSOLUTE ERROR - Large System

Winner: Least Squares with team home field advantages

I think we have pretty much established what systems do certain things
well retroactively. Least squares using team specific home field advantage wins this award
for the seventh straight year. It had an average error of 9.0704 which is relatively
high and down from the record of 8.4189 set last year.

Winner 2006: Least squares with team specific home field advantage
Winner 2005: Least squares with team specific home field advantage
Winner 2004: Least squares with team specific home field advantage
Winner 2003: Least squares with team specific home field advantage
Winner 2002: Least squares with team specific home field advantage
Winner 2001: Least squares with team specific home field advantage
Winner 2000: Least squares with team specific home field advantage

SMALLEST RETRODICTIVE ABSOLUTE ERROR - Simple System

Winner: Least Absolute Value regression

The top 5 systems in this category all use individual team home field advantages. The
best system that doesn't was least absolute value regression, L1 L1 wins this category
this year with an mean error of 9.3804. L1 set the record last year with 8.997

Winner 2006: Least Absolute Value Regression
Winner 2005: Least Absolute Value Regression
Winner 2004: Sagarin Points
Winner 2003: Sagarin Points

SMALLEST RETRODICTIVE BIAS

Winner: Least Absolute Value regression

The smallest bias seen in 2006 was also in least absolute value regression with
a value of +0.0286, about the same magnitude as the winner last season. Only nine
systems had values less than zero this year. This is an interesting category because
many systems always end up with almost identical numbers. This year 14 systems had
values right around +1.

Winner 2006: Least Absolute Value Regression
Winner 2005: Sports Report Elo
Winner 2004: CPA Rankings
Winner 2003: CPA Rankings
Winner 2002: PerformanZ Ratings
Winner 2001: Herman Matthews
Winner 2000: Massey Ratings

MOST ACCURATE SYSTEM - SMALLEST MEAN SQUARE ERROR - Large system

Winner: Least Squares with team home field advantages

As with absolute error, Least squares with team specific home field advantage
takes this award for the seventh straight season. The winning mean square
error was 127.1576. CPA Rankings has inched a little closer each of the last
two years but has yet to break through.

MOST ACCURATE SYSTEM - SMALLEST MEAN SQUARE ERROR - Simple system

Winner: The Sports Report

The most accurate system without a team specific home field advantage was
The Sports report predictive rating. They have two other ratings they do
incorporate team specific home field advantage. The Sports Report's average
mean square error was 144.517. This was only good for 7th place overall.

Winner 2006: The Sports Report
Winner 2005: The Sports Report
Winner 2004: Least Square Regression
Winner 2003: Sagarin points

BEST OVERALL RETRODICTIVE SYSTEM - Large System

Winner: The Sports Report

As with the other overall awards, points are assigned to systems in each category then
summed up. The system with the most points wins.
This year TSR SLOTS won without any serious competition. SLOTS does well across the board
retroactively but always dominates the wins category. TSR Elo and CPA Retro are the
other strongest systems this year.

Winner 2006: TSR SLOTS
Winner 2005: TSR SLOTS
Winner 2004: Least Squares with team home field advantages
Winner 2003: TSR SLOTS
Winner 2002: Least Squares with team home field advantages
Winner 2001: CPA Rankings
Winner 2000: CPA Rankings

BEST OVERALL RETRODICTIVE SYSTEM - Small System

Winner: Sagarin Predictive/Points

Among the systems without team specific home field advantages I give the overall title to
Jeff Sagarin's main rating. This system was good for 6th place overall but it was the highest among the
'simple' systems. The system closest behind was a new entry for this year, Roger Johnson.

Winner 2006: Jeff Sagarin
Winner 2005: Sagarin Points
Winner 2004: Sagarin Points
Winner 2003: Frank Alder