- 19 August 2006 The 2006 Distance Matrix
- Division 1A football moves to a permanent 12-game season in 2006, but the schedule topology doesn't look like the 2002-03 years when most 12th games improved the field connectivity.
17 October 2006 Calculating the Distance Matrix Defining some terms as I've (possibly incorrectly) used them.
28 October 2006 Analyzing the Games Graph Effects of connectivity on rating systems.
- 25 August 2006 Correlating Computer Rankings
- Two summaries that can be used to order teams by their computer rankings.
- 31 August 2006 Update to Correlating Rankings
- An Updated and corrected version of the meta ranking.
- 14 September 2006 Interdivisional Results
- Another look at scoring data in inter-divisional games. Weekly update.
- 15 September 2006 The Flaw In the Polls
- An example of what can happen now that the BCS is almost entirely based upon the human polls.
- 27 September 2006 Alternative Vote Counts
- Example of different vote-counting techniques using real ballots.
9 October 2006 AP Week 6 Even realer data, since the AP began publishing all ballots this week.
16 October 2006 Week 7 (Poll #8)
22 October 2006 Week 8 (Poll #9)
29 October 2006 Week 9 (poll #10)
5 November 2006 Week 10 (poll #11)
12 November 2006 Week 11 (poll #12)
19 November 2006 Week 12 (poll #13) - with an editorial on the AP's "Credibility"
26 November 2006 Week 13 (poll #14) - even more interesting manipulations
3 December 2006 Week 14 (final regular season)
11 January 2007 Final
- 21 October, 2006 Introducing the Resume Report.
- 27 October, 2006 A second look at the schedule after eight weeks.
- 9 November, 2006 Home Field Advantage?
- 15 November, 2006 Victory Chain Counts
- 21 November, 2006 Victory Chain Counts as a Second-Order winning percentage
- 27 November, 2006 Scoring Summary after week 13 Nearly final results.
- Conference name in the header links to consolidated schedule for all conference teams. Team names link to the teams' schedules.
- Schedule & Results (Division 1) (Scores in CSV Format)
All NCAA and NAIA results by week beginning:
Aug 24 _ 31 Sep 7 _14 _21 _28 Oct 5 _12 _19 _26 Nov_2 _9 _16 _23 _30 Dec_8 _15 _21 _28 Jan_6
(source: Peter Wolfe's schedule page, scores from various sources.)
- Games Graph (How teams are related by Opponents' Opponents chains):
- Current 1A All D-1
Path Counts: Division 1A All D-1
- Wins Graph (How teams are related by victories over teams with victories over...):
- #Teams at each distance % teams "defeated"
(The indexes link to details for each team.)
All Division I
- Records vs Common Opponents
- This report is not very user-friendly, so this year it is complemented by a consolidated schedule of all of each team's opponents.
- Opponents' schedules and results by team.
A consolidated schedule for each team including all their opponents' games. Opponents are italicized.
- Team resumes
- Results for each team and opponents' scoring stats against other teams.
- Normalized Scoring Statistics
- Applies the Iterative Strength of Victory data to normalize points scored and allowed based upon opponents' strength.
- Strength of Schedule Division 1-A Only
- An accurate winning percentage-based SOS.
A 1-line summary of Best Win, Worst Loss, Toughest Remaining Opponent, along with wins, losses, and remaining opponents-rank lists. *indicates road games, and conference opponents' ranks are underlined within the lists.
- Interconference Records
- Conference vs conference results with strength of opponent defined by Sagarin's Predictor considered.
ISOV conf v conf - SOS defined by opponents' ISOV
ISR conf v conf - SOS defined by opponents' ISR
- Bowl Affiliations Bowl Schedule
- Polls: Current AP History USA Today (Coaches) History Harris Poll History
College Football Rankings comparison
An invaluable resource compiled by Kenneth Massey. See the Bucklin Majority meta-ranking for one use of it.
David Wilson's Ranking List
Categorizes the rankings by type and links to current versions.
Offensive and defensive statistics
Often people who are not familiar with the nature and limitations of statistical methods tend to expect too much of the rating system. Ratings provide merely a comparison of performances, no more and no less. The measurement of the performance of an individual is always made relative to the performance of his competitors and both the performance of the player and of his opponents are subject to much the same random fluctuations. The measurement of the rating of an individual might well be compared with the measurement of the position of a cork bobbing up and down on the surface of agitated water with a yard stick tied to a rope and which is swaying in the wind.
Arpad Elo in Chess Life, 1962
In theory, there is no difference between theory and practice; In practice, there is.