Sunday, December 21, 2008

Conference tournaments

I've started making (at least) weekly forecasts which include simulated conference tournaments. It is always a pain to go through all 30 conference tournament formats each year and figure out how they have changed since last year. If you see any problems, let me know. Here's what I do:

After each of the 10,000 simulated seasons:

1. Figure out seeds based on records
2. Run a simulated tournament
3. Calculate RPI for that one simulation

I repeat this for all 10,000 simulations. For each team, I report RPI broken down by different end-of-season records which will include every scenario that happened in the 10,000 simulations. To give you an idea of what I'm talking about, here is the page for Utah State of the WAC:

http://www.rpiforecast.com/teams/ct/Utah%20St..html

Through Games of Dec 20, the WAC conference tournament looks like it will help USU on average by a few spots. Without taking into account the tournament, their Expected RPI is about 46. Once the simulated tournament is added, it becomes about 43 - a slight improvement. For some teams, the conference tourneys will be a huge boost. This is especially true for teams which have byes until later rounds. One of the problems with conference tournaments (at least in terms of RPIs) is that teams with high seeds are paired up with low seeded teams until the final rounds of the tournament. This will tend to hurt their RPIs even if they win. If I were on the chairman of a mid-major conference, given the choice, I would choose a format with byes for the top seeds.

Monday, December 8, 2008

Thanks Ken.

As some of you know, Ken Pomeroy has stopped publishing the day-to-day RPI. I just came across this newspaper article about the topic and noticed this bit:

Q: Where should fans go now?
A: There's a Web site called
RPIforecast.com; what the guy does there is he projects the end-of-season RPI.
That's probably more useful.



Thanks for the plug, Ken. Ken has always been more than helpful. I think we both agree that the RPI is not the best measure of a team's quality. My philosophy is that as long as the NCAA is going to use it, why not try to predict what it will be come tourney time.

Tuesday, November 11, 2008

New Season

With the new season underway, I've started making projections again. Keep in mind that because it is very early in the season, the probabilities (which are from Sagarin's PREDICTOR) are partly based on past seasons. Within a few weeks this will no longer be the case. This season, updates might be more sporadic than last year, especially during January and February, but I should still be able to update every day.

Monday, March 10, 2008

Conference Tourney Upsets

Bubble teams (and their fans) all over the country will be pulling for favorites to win the conference tournaments this week, especially when the favorite would otherwise likely get an at-large bid. We've already seen VCU lose in the CAA tournament. They are now definitely on the bubble with about a 40% chance of an at-large bid. They probably didn't burst anybody's bubble but their own.

The tournament that may very well burst a bubble is the MAC tourney. Kent State has a very strong case for an at-large bid even with a loss in the MAC tournament. I'd say they have about a 75% chance of an a bid if they don't get the automatic bid. No other MAC team has much of a case. However, Kent State only has a 25% chance of winning the tournament. In fact, Akron is slightly more likely to win based on Sagarin's PREDICTOR:


Team (Seed) Prob(Auto Bid)
Kent St. (1) 25.8%
Western Michigan (2) 18.0%
Akron (3) 26.7%
Ohio (4) 11.7%
Miami OH (5) 15.3%
Central Michigan (6) 1.3%
Eastern Michigan (7) 0.6%
Toledo (8) 0.3%
Bowling Green (9) 0.2%
Ball St. (10) 0.1%
Northern Illinois (11) 0.0%
Buffalo (12) 0.0%

So, there is basically a 75% chance that the MAC tournament will burst somebody's bubble (other than Kent State's). In no other conference tournament is it more likely than not that a team with no at-large bid chance will steal the automatic bid from a team that's a near lock for an at-large.

Tuesday, March 4, 2008

Updates

Today marks the first day of conference tournament play. The basic RPI Forecast doesn't include conference tournaments. For that reason, I added the forecasts that do include them which are updated a couple of times per week: http://www.rpiforecast.com/ct/index.html

Now that conference tournament season is upon us, I'll start updating that page more frequently (probably every day). The main page will only include conference tournament games that have already been played. If you want to see all of the possible outcomes along with the expected RPI for each scenario including conference touranments, go to the above link and click on your team. Next year, the forecasts which include conference tournaments will become the standard forecasts.

As explained in detail below, the seedings for conference tournaments are determined for each of the 10,000 simulated regular seasons, and a simulated tournament is run for each of the 10,000 simulations. By now, many of the conference tournament seeds are already set in stone. If a team does as expected in the conference tournament, their end of regular season RPI will typically be very close to their end of conference tournament RPI.

Tuesday, February 26, 2008

Updates

Updates were slow for a few days because I'm on vacation in Miami and am without regular internet access. That should only last a few more days.

Tuesday, February 12, 2008

Conference Tournaments

I have been updating the pages that include confernce tournaments a couple of times per week (not necessarily on Mondays). One thing to remember for seeding purposes, is that when two or more teams are tied, I'm randomly assigning the higher seed to one of them. To incorporate all of the tiebreaker rules for all of the conferences would be mind-numbing and will probably not affect the results much at all.

Monday, January 21, 2008

Team Pages added for Conf Tourney Forecasts

I decided to go ahead and add the team pages that include the conference tournament forecasts in the simulations (as described in the previous post). I may add more info for next week. Just click on a team's name on the page:

http://www.rpiforecast.com/ct/index.html

Projections INCLUDING Conference Tournaments

There have been many requests to incorporate the conference tournaments into the simulations. I have started doing that on a weekly basis on a separate page:

http://www.rpiforecast.com/ct/index.html

I will update this on Mondays to start. We'll see how that goes.

Here's the procedure:
1. Run the simulations as usual.
2. At the end of each simulated regular season, sort teams in each conference (or division) based on its record.
3. From the conference records in #2, seed the teams for the conference tournaments
4. If two or more teams are tied, the seeds are randomly picked between the tied teams (Learning and incorporating all of the complex tiebreakers for every conference is just too time consuming)
5. For all 30 conferences that hold tournaments, run a simulated tournament based on the specific structure and home court advantages of each tournament.
6. Calculate RPIs, SOS, and the other usual stats for the entire season including the tournaments.
7. Run the simulations 10,000 times

Anyway, eventually I'll add individual team pages (maybe next week) that include the conf tournament forecasts. Items included will be things like probability of winning tournament, expected number of wins in the tournament, etc.

Wednesday, January 16, 2008

BracketBuster update

I updated the Bracketbuster RPI forecasts. Remember that these are forecasts of what the RPIs, records, etc. will be on Sunday, Feb. 3, which is the day that the big wigs get together to decide the initial matchups in the Bracket Buster games. As usual, the W-L forecasts are rounded to the nearest digit since they are expectations. If you want to figure out exactly what they are, simply add up the probabilities of winning over the remaining games to get the expected number of wins. The expected numer of losses is then easy to infer. Here's the page:

http://www.rpiforecast.com/bb.html

Wednesday, January 2, 2008

BracketBusters

For those of you who are interested in the ESPN BracketBuster matchups, I performed a little exercise. The beauty of the RPI Forecast methodology is that not only can you forecast the RPI at the end of the season, you can predict it for any future date.

With that in mind, I decided to provide a forecast of what it will look like on February 3, 2008. That is the date that the powers that be will get together to decide the initial parings for the Bracket Buster matchups. I'm fairly certain that the RPI is only a very small factor in those decisions, with money (TV ad revenues) being the largest. Nevertheless, records and RPIs are likely to have some influence on the decision.

Anyhow, here is the page with the teams sorted by RPI Forecast (for February 3) and separated into the 50 home teams and 50 road teams so that you can make your own predictions. Enjoy:

http://www.rpiforecast.com/bb.html

I will NOT be updating that particular page daily. If I make any futher updates, I'll make it known.

EDIT: The page temporarily reverted to one that I had from last season. It has now been fixed.