So, the season is finally upon us. Over the summer, I developed a basketball ranking system similar to Ken Massey's rankings. I've made some adjustments to his ideas. The biggest difference is that while Massey takes into account all games across all divisions, my system only includes games between Division III teams. By replaying last year's season day-by-day, my system predicted the winner of roughly 74% of the games.
I hope to have at least weekly ratings, which I will link to from the boards. I have a basic website setup. Right now, all that is there is an explanation of the system, last year's final top 50, and to hopefully get some excitement for the season upcoming season, I've posted estimated margins-of-victory for tomorrow's games (Note: these are estimated basically by using last year's final rankings, thus they will be much less accurate until a sufficient number of games are played).
This was just a little fun experiment to better understand ranking systems but I figured the results from last year were pretty good so why not share it with others that might be interested. Let me know if you have questions...below is the link:
https://sites.google.com/site/d3basketballindex/ (https://sites.google.com/site/d3basketballindex/)
Brilliant. Absolutely love it!
My only sad is that no Presque Isle ratings. :-[
Otherwise ;D ;D ;D
I think that you underrepresent the ASC and schools in Texas. We have few chances to play teams from outside the area. Therefore the interaction necessary to predict the strength of a team is missing. I believe that ASC Champ and ASC-West Division winner McMurry, ASC-East champ UT-Dallas and Sweet 16 (Pool C) UMHB were all Top 50 teams last season.
To accomodate Centenary, the conference will play 8 crossover games and 14 district games.
That leaves only 3 non-conference games, and few dates to play those opponents. The one way that you can help the isolated teams is to include non-D-III scores.
Thanks for the effort.
The MIAC schools can only play 4 non-conference games each. They have 6 teams ranked on augie_superfan's excellent ranking.
Quote from: sac on November 15, 2011, 01:48:34 PM
The MIAC schools can only play 4 non-conference games each. They have 5 teams ranked on augie_superfan's excellent ranking.
Thanks for the comment.
Yes, but there are several other schools around the MIAC to which the computer rankings can link. Their near-by universe is much more "robust", (I hope that that term is representative of the statistical modeling.)
I think the effort is to make this a closed universe, as a more open universe makes it difficult to put the value proposition on outside-D3 teams. If you want this to be a robust ratings system, you need to filter out 'noise' and arbitrary saying this D2 team has this value or this USCAA team has that value makes it harder to really peg a true value.
Even with a limited slate of non-conference games there should be enough of a cross-over to connect the ASC teams to the rest of the universe. They're not the NESCAC in football!
Thanks, smed. My concern about the validity of his rankings is that UMHB finished #16 at the end of the season on the "big poll". UT-D received votes last year (RV #33) after losing in the ASC-Semi-finals to McMurry and then losing the first round game as a Pool C bid to UMHB. The statistical model has neither in the Top 50. Using last year's results in a D-III universe, then you are likely to understate the quality of play in the ASC.
After removing the playing dates that the ASC mandates for crossover play, that only leaves about 1 week at the start of the season and Christmas break. That makes it difficult to find D-III opponents. I find 17 games against 5 SCAC-West schools. Hardin-Simmons goes to Las Vegas for 2 games and UW-Stout comes to Belton (UMHB) in December. Other than that there is very little cross over.
I can accept that, but all that use the tool may not be aware of that problem.
Quote from: Ralph Turner on November 15, 2011, 05:59:31 PM
Thanks, smed. My concern about the validity of his rankings is that UMHB finished #16 at the end of the season on the "big poll". UT-D received votes last year (RV #33) after losing in the ASC-Semi-finals to McMurry and then losing the first round game as a Pool C bid to UMHB. The statistical model has neither in the Top 50. Using last year's results in a D-III universe, then you are likely to understate the quality of play in the ASC.
After removing the playing dates that the ASC mandates for crossover play, that only leaves about 1 week at the start of the season and Christmas break. That makes it difficult to find D-III opponents. I find 17 games against 5 SCAC-West schools. Hardin-Simmons goes to Las Vegas for 2 games and UW-Stout comes to Belton (UMHB) in December. Other than that there is very little cross over.
I can accept that, but all that use the tool may not be aware of that problem.
Ralph,
I completely agree with you that the lack of out-of-conference games for the ASC and other isolated schools can lead to issues in the rankings. However, the issue is not that it automatically misrepresents the league on the lower side. It would just mean there is less information to come to a conclusion. All games have the same significance, more games for one conference just gives more information to better fit the data, not actually any advantage to that conference.
Where I do agree with you is when you look at the excluded games in my system. I agree that more information is probably better but it's hard to tell without building two systems and comparing them. Unfortunately I dont have the time to track all basketball teams. When you look at specific teams you can pick out where there may be issues. As you mentioned, McMurry was a team that probably should've been rated a bit higher if all games were included. I see 2 games, a close loss to Southern Methodist and a blowout win against Barclay. By looking at Massey's rating from last year I see that both of these were what I would call as "over-performances"...meaning games where they beat the expectation by a lot (actually major over-performances). By leaving these out, my system then underestimated their true ranking with all info included. If I scale my rankings with this info than it would raise their ranking from roughly #63 to #48. This actually seems to be an extreme case so I'm glad you brought it to my attention.
If I can get some time, I will try to take a look at some of the other ASC teams and see if games that were excluded would've been considered over or under performances.
I had given some thought to not tracking every team but having "dummy" teams like "D1 Top 25", "D1 25-100", "D2 1-50", etc. to account for the game and the opponents strength. It would only add the tracking of maybe 30 "teams" instead of thousands more....maybe next year!
Quote from: sac on November 15, 2011, 01:48:34 PM
The MIAC schools can only play 4 non-conference games each. They have 6 teams ranked on augie_superfan's excellent ranking.
Actually one of the things that got me interested in these rankings systems last year was the MIAC's dominance in the rankings. I couldn't believe that the Massey ratings were right in having teams like Carleton, Hamline, and Gustavus Adolphus up in the Top 10-25. Mine rated them a bit lower but not as much as I would've thought.
This is the fun of my system, the chance to talk about what you agree and disagree with, all the opinions give me more things to look at and hopefully for ways to make it better....thanks for the feedback.
+1 on this ranking. Very Cool. 8-) You had scoring pretty dead on. Cabrini beat Haverford by 12. :)
Quote from: mailsy on November 15, 2011, 09:38:26 PM
+1 on this ranking. Very Cool. 8-) You had scoring pretty dead on. Cabrini beat Haverford by 12. :)
Anything this early in the season is just plain luck...the system has no information to go by except last year's final rankings...thus it doesn't take into account the changes of team strength via graduation, new players, etc.
I'm sure there are plenty games tonight that are off by more than 20 points. Thanks for checking out the rating though...keep checking back.
Augie, I can understand the Barclay and SMU games for McMurry.
The more problematic question is why are UMHB (#16) and UT-Dallas (RV #33) not even found in the Top 50!
Thanks for the good work! +1!
I think maybe I miscommunicated what the "Top 50" were that I posted. Those were the Top 50 in my system from the end of last year. I think you are taking the #16 and #33 from this year's preseason poll. It looks like at the end of last year, UMHB was ranked #20 and UT-D was ranked #44. In my final ranking, they were #68 and #57 respectively. If the full McMurry data was in the system, I estimate it would've moved UMHB up roughly 6 spots due to them playing 4 times last season.
If you go and look at the Week 13 poll, they were ranked, UMHB(#44) and UT-D(#33). So UMHB made a major move in the polls due to 3 games whereas those 3 games affect my system little because they slightly over-performed twice and then under-performed at Augustana. Now, in the eyes of a human voter, these were 3 big games and thus why there was a large movement in their rank. However, for my system, these games could've been played the first week of the season or the last and my system didn't care. Now, there are some other ranking systems that feel differently than this and either weight tourney games more or recent games more, etc . So, I think if trying to compare these apples and oranges, we could actually also compare the numbers of UMHB(#44 vs. roughly #62) and UT-D(#33 vs. #57).
But this is precisely why you can't compare these rankings to the human polls because they are based off different "inputs" in a way. Also, other human voters probably "weight" games differently in their mind. Is a human poll supposed to take into account every game of the season with the same weight or should a team get more credit for winning in the tournament? That's a question that I don't think there is a right or wrong answer to.
Thanks for the comments
Humans vote emotionally, and I think they weight the more current games highly as they vote. The beauty of these ratings system is that they take the results as a whole. Of course, they can't filter out injuries, travel, and other issues. But you need both the emotion and the cold hard facts of life.
My bad! Thank you for the clarification.
I did not check the browser to confirm the URL when I made that post. I thought that I was on the Final 2011 poll when I quoted the #16 and #33 rankings.
http://www.d3hoops.com/top25/men/2010-11/final
Living in a world where Confidence Intervals, Odds Ratios and Relative Risk are not natural, but imposed upon me, I look at these indices and wish for them to be displayed as a figure with standard deviations demonstrated. :)
Among 420 schools that play men's basketball, we are discussing the top Decile. Also, I stated on another board, I think that a plane flight is worth 7 points in Home Court Advantage. The flight back for the home team to become the visitor makes that a 14-point swing. Pat Coleman quoted a coach's assessment that is was "20 points" when one got on a plane.
I like "7 points" more than the "20 point" swing. I hope that we can keep that in mind as teams travel over the holidays.
Quote from: Ralph Turner on November 17, 2011, 09:39:05 AM
Among 420 schools that play men's basketball, we are discussing the top Decile. Also, I stated on another board, I think that a plane flight is worth 7 points in Home Court Advantage. The flight back for the home team to become the visitor makes that a 14-point swing. Pat Coleman quoted a coach's assessment that is was "20 points" when one got on a plane.
I like "7 points" more than the "20 point" swing. I hope that we can keep that in mind as teams travel over the holidays.
Actually, that could be an interesting study. augie_superfan, would you be able to look at that with last year's data? How much did teams that had to fly across the country under perform expectations?
Quote from: KnightSlappy on November 17, 2011, 09:53:29 AM
Quote from: Ralph Turner on November 17, 2011, 09:39:05 AM
Among 420 schools that play men's basketball, we are discussing the top Decile. Also, I stated on another board, I think that a plane flight is worth 7 points in Home Court Advantage. The flight back for the home team to become the visitor makes that a 14-point swing. Pat Coleman quoted a coach's assessment that is was "20 points" when one got on a plane.
I like "7 points" more than the "20 point" swing. I hope that we can keep that in mind as teams travel over the holidays.
Actually, that could be an interesting study. augie_superfan, would you be able to look at that with last year's data? How much did teams that had to fly across the country under perform expectations?
i agree. I would arbitrarily assume that a 500 mile trip, either by bus or by plane, is the 7-point difference.
A 500-mile flight by both teams to a neutral site would cancel out. Most indices like 3 points as home court advantage in most (local) games.
How UAA teams handle it might be an interesting sub-group?
Of course, it may be different when teams have a tournament and have time to get acclimated instead of a one-off.
Quote from: smedindy on November 17, 2011, 02:45:55 PM
Of course, it may be different when teams have a tournament and have time to get acclimated instead of a one-off.
That might show up in the sub-set of "second night tourney games".
Quote from: KnightSlappy on November 17, 2011, 09:53:29 AM
Actually, that could be an interesting study. augie_superfan, would you be able to look at that with last year's data? How much did teams that had to fly across the country under perform expectations?
Yeah, I could run through that at some point. For last year, I basically have each game and it's predicted margin at the time of the game and then of course the actual score. So I could easily compare how teams did that flew as opposed to the other games....I'd just have to identify those games in which teams flew. Easy ones would be the tourney games. Obviously some Thanksgiving/Christmas tournament games. Are there any teams in the South/West regions that have to fly for any of their conference games? I guess just about any SCIAC vs. NWC games would require a flight, right?
That is why I selected the 500 mile limit. :)
You can get the mileage from the TES system at the NCAA.
500 miles on a bus or a flight to some school 500 miles away is still a long way from the fan base and is a night or 2 on the road.
Updated predictions for tonight's games on the website:
https://sites.google.com/site/d3basketballindex/nov-18-2011-predictions (https://sites.google.com/site/d3basketballindex/nov-18-2011-predictions)
NOTE: Still has a big reliance on last year's rankings so the accuracy is limited. Also, it assumes the team listed as HOME on the D3Hoops scoreboard page is indeed the home team. With all the tourneys this weekend, a ton of games are at neutral sites. If this is the case, just add 2.5 points to the margin listed to get the neutral margin.
Enjoy!
Updated rankings for all teams thru Friday's games. Also have predictions for today's games updated on the website.
https://sites.google.com/site/d3basketballindex/
Prediction results thru 11/18/2011: 76.7% of games correct
NOTE: Rankings are still heavily reliant on the preseason ratings. Enjoy.
Updated rankings thru Sunday's games:
https://sites.google.com/site/d3basketballindex/ (https://sites.google.com/site/d3basketballindex/)
Also have predictions for the full slate of games Tuesday:
https://sites.google.com/site/d3basketballindex/nov-22-2011-predictions (https://sites.google.com/site/d3basketballindex/nov-22-2011-predictions)
Some tight projected "Top 25" games tomorrow:
No. 8 St. Thomas | No. 21 UW-River Falls | 1 |
Capital | No. 11 Wittenberg | -1 |
No. 20 Centre | Transylvania | 0 |
Is the rating number basically points above average?
Also, Maine-Presque Isle and Nebraska Wesleyan are D3 teams.
He talked about them in his explanation, KnightSlappy. They don't have enough D3 games to map properly.
Then carry on!
Quote from: KnightSlappy on November 22, 2011, 09:50:27 AM
Is the rating number basically points above average?
Yes, the way the rankings are scaled means you can interpret the value as the margin vs. an "average" team on a neutral floor.
Quote from: KnightSlappy on November 22, 2011, 09:50:27 AM
Also, Maine-Presque Isle and Nebraska Wesleyan are D3 teams.
Over the long weekend, I'm going to rerun the games with M-PI and NW in them to see if there is much difference. M-PI plays most of their D3 games upfront so, on second look, they should probably provide good data. I think NW is pretty much the same way so we will see.
Quote from: augie_superfan on November 22, 2011, 12:04:37 AM
Updated rankings thru Sunday's games:
https://sites.google.com/site/d3basketballindex/ (https://sites.google.com/site/d3basketballindex/)
Also have predictions for the full slate of games Tuesday:
https://sites.google.com/site/d3basketballindex/nov-22-2011-predictions (https://sites.google.com/site/d3basketballindex/nov-22-2011-predictions)
Some tight projected "Top 25" games tomorrow:
No. 8 St. Thomas | No. 21 UW-River Falls | 1 |
Capital | No. 11 Wittenberg | -1 |
No. 20 Centre | Transylvania | 0 |
Transylvania 72 Centre 64
Wittenberg 69 Capital 63
River Falls 79 St. Thomas 64
After some great games and some Top 25 upsets last night, I have updated the rankings on my website. I have a full listing of all rankings and the Top 75 also updated through Tuesday night's games.
System prediction results so far:
Correctly predicted winner: 75.9%
Margin correct within 5 points: 64.7% of the time
Margin correct within 10 points: 77.8% of the time
Margin correct within 15 points: 88.1% of the time
Predictions for Friday's games:
https://sites.google.com/site/d3basketballindex/nov-25-2011-predictions (https://sites.google.com/site/d3basketballindex/nov-25-2011-predictions)
Have a good Thanksgiving!
Saturday's games:
https://sites.google.com/site/d3basketballindex/nov-26-2011-predictions
Also have updated rankings
This is awesome.
Quote from: CityD3 on November 26, 2011, 08:07:18 PM
This is awesome.
Thanks CityD3, glad you enjoy.
Here are today's predictions:
https://sites.google.com/site/d3basketballindex/nov-27-2011-predictions (https://sites.google.com/site/d3basketballindex/nov-27-2011-predictions)
Expect an update to the website after tonight's games. Full rankings for all teams, and also expect for the first time this year:
Conference Rankings and
Team Strength of Schedule Ratings
Updated thru Sunday's games:
https://sites.google.com/site/d3basketballindex/ (https://sites.google.com/site/d3basketballindex/)
I have full rankings, Top 75 rankings including SOS rankings, separate SOS page with all teams and conference rankings
Enjoy!
Having UMHB and UT-Dallas in the Top 75 is good.
Got the updated predictions for today's games online now:
https://sites.google.com/site/d3basketballindex/dec-3-2011-predictions (https://sites.google.com/site/d3basketballindex/dec-3-2011-predictions)
The Top 75 and Full Rankings are updated also and I will have the rest updated after the full slate of games today.
Site has been update thru Sunday's games: https://sites.google.com/site/d3basketballindex/ (https://sites.google.com/site/d3basketballindex/)
As of today's rankings, there is no longer any preseason bias. As of today, the system has predicted 1088 out of 1441 games correctly (75.5 %). Hopefully that percentage will continue to improve as more games are played.
The top team is currently Hope. This is bolstered by winning their only two Division III games with one of those being over highly ranked (#5) Wheaton.
Enjoy!
I check out these rankings all the time and have found them to be pretty accurate. I prefer them to Massey's. Keep up the good work. Plus K
Updated the site through today's games (except for the yet to be finished Widener @ Occidental game).
Final regular season prediction results:
3719 correct out of 4970 games = 74.83%
I have added a page that has my system's bracket prediction for the entire tournament. I also have a page that shows the Round 1 games, the predicted winner, the predicted margin and the "odds" of winning that round. These will be updated after each round for the next matchups.
https://sites.google.com/site/d3basketballindex/ (https://sites.google.com/site/d3basketballindex/)
Augie, how much did you give for Home court advantage?
Thanks.
Used 3 points for the playoffs...had 2.5 all season long but it came out closer to 3 on the year so I figured to just use that. However, I can only do that for the first two rounds. I also don't have any effect for teams that will be flying, like Whitworth. So, for a potential UMHB vs. Whitworth matchup, my system tells me Whitworth in basically a toss-up but my head tells me to take UMHB.
Obviously the home-court advantage has a big potential to affect the S16 and E8 games but I can't predict the host team so I can't apply the HCA for those rounds.
Quote from: augie_superfan on February 28, 2012, 12:43:17 AM
Used 3 points for the playoffs...had 2.5 all season long but it came out closer to 3 on the year so I figured to just use that. However, I can only do that for the first two rounds. I also don't have any effect for teams that will be flying, like Whitworth. So, for a potential UMHB vs. Whitworth matchup, my system tells me Whitworth in basically a toss-up but my head tells me to take UMHB.
Obviously the home-court advantage has a big potential to affect the S16 and E8 games but I can't predict the host team so I can't apply the HCA for those rounds.
My bias is that a plane flight in D3 is worth about 7 points. I think that McMurry gains 4 net points due to travel.
Whitworth will be the best fundamental team that we have seen this season.
augie,
Great work as usual. Plus k.
Quote from: Ralph Turner on February 28, 2012, 01:05:48 AM
Quote from: augie_superfan on February 28, 2012, 12:43:17 AM
Used 3 points for the playoffs...had 2.5 all season long but it came out closer to 3 on the year so I figured to just use that. However, I can only do that for the first two rounds. I also don't have any effect for teams that will be flying, like Whitworth. So, for a potential UMHB vs. Whitworth matchup, my system tells me Whitworth in basically a toss-up but my head tells me to take UMHB.
Obviously the home-court advantage has a big potential to affect the S16 and E8 games but I can't predict the host team so I can't apply the HCA for those rounds.
My bias is that a plane flight in D3 is worth about 7 points. I think that McMurry gains 4 net points due to travel.
Whitworth will be the best fundamental team that we have seen this season.
Another item that's difficult to capture, but which I'm trying to use as a subjective factor in my analysis of the early round matchups are the "near home" neutral site games.
For example, in Wooster's pod, Capital and it's fan base has a nice, short, 100 mile trip up to Wooster to face Randolph-Macon and their 440-mile, 8+ hour bus trip. I don't know how well the RMC fan base travels, but I suspect that the first game on Friday will have a near home game feel for the Crusaders, even if it is a "neutral site" by the books.
Quote from: Ralph Turner on February 28, 2012, 01:05:48 AM
Quote from: augie_superfan on February 28, 2012, 12:43:17 AM
Used 3 points for the playoffs...had 2.5 all season long but it came out closer to 3 on the year so I figured to just use that. However, I can only do that for the first two rounds. I also don't have any effect for teams that will be flying, like Whitworth. So, for a potential UMHB vs. Whitworth matchup, my system tells me Whitworth in basically a toss-up but my head tells me to take UMHB.
Obviously the home-court advantage has a big potential to affect the S16 and E8 games but I can't predict the host team so I can't apply the HCA for those rounds.
My bias is that a plane flight in D3 is worth about 7 points. I think that McMurry gains 4 net points due to travel.
Does the travel spread go up or down depending upon the quality of the in-flight movie? ;)
I've now added a new page to the website labeled "Tourney Odds"
https://sites.google.com/site/d3basketballindex/tourney-odds (https://sites.google.com/site/d3basketballindex/tourney-odds)
I simulated the tournament 1 million times (dont worry, only takes the computer about 7 minutes). What resulted is a list of what percentage of times each team wins in each round. There are examples of how to interpret the table of values on the webpage.
The percentages are taken from the two competing team's ratings as determined by my ranking system. There are some intersting things that can be seen in the table such as which "pods" or regions are teh easiest and which are the hardest. Also other interesting things, for example:
My system has MIT rated slightly higher than Amherst (1 point better on a neutral court). They have a possible matchup in the Elite Eight. You would then think that my system would predict MIT to go to the Final Four more often, however the opposite actaully happens. It has Amherst making the Finla Four 29.1% of the time and MIT 26.3% of the time. Why is this? Simply because MIT has a more difficult road to even get to that game. Amherst is predicted to be in that Elite Eight game 49.9% of the time whereas MIT is predicted to be there only 42.8% of the time.
*NOTE: Home court advantage is only taken into account for rounds 1 and 2. All other games are assumed to be neutral court. I will update the values once the Sectional hosts are decided.
Is this coming back this season, augie?
Quote from: CityD3 on December 01, 2012, 01:34:46 PM
Is this coming back this season, augie?
I asked him the same question back in early November with a PM. His reply was not at this time due to family commitments. I miss his rankings and predictions which I referenced more than Massey's. Hopefully at some point in the future augie will return to give us a great source of D3 matchups.