We've added a page that lists the probabilities for reaching each of the rounds of the tournament - along with winning it all - for all 68 teams.
The page is here: http://www.rpiforecast.com/tourneyprobabilites.html
There are two types of probabilites listed: UNCONDITIONAL and CONDITIONAL
You are probably most familiar with UNCONDITIONAL. That tells you the overall probability of a team reaching each of the rounds. The CONDITIONAL probabilities, however, tell you the probability that a team reaches a round given that it has already reached the previous round. For example, a team like UT-San Antonio may have a very low unconditional probability of reaching the Final 4, however, conditional on it having already reached the Elite 8, it will have a much higher probability. We'll update the webpage as we reach each new round with new probabilities. These will change as teams (and potential future matchups) are eliminated.
Monday, March 14, 2011
How'd we do?
The main goals (and the main strengths) of this site are (1) to provide accurate predictions of end-of-season RPI, and (2) to provide up to the minute current RPI. A secondary goal is to provide predictions of at-large bids and seeds. Up until this season, we were not predicting seeds, just bids. This season, we decided to use the "Dance Card" formulas for seeds in addition to the at-large formulas. In terms of at-large bids, we did a bit worse than seasons past - missing 3 (VCU, USC, and Florida State). However, only one major bracketologist got even 67 out of 68 (Fox Sports). As far as I have seen, nobody got 68. Based on the Bracket Project website, only a handful got 66 or better. Most were 65 or less, so 3 is nothing to be ashamed of - especially considering the fact that this is all done using a simple formula. Typically the Dance Card formula misses no less than 1 or 2, so this season was unusual.
As for seeds, there IS something to be ashamed of. Quite simply, the seed predictions stunk! In the name of objectivity, we wanted to avoid tweaking the seeds and let the formulas do all the work. However, something obviously needs to be done. The plan for next season is probably to abandon the formulas for seeding - or at least to modify them to allow for some "human analysis". We'll stick with the at-large formulas and figure out a better way to seed the teams. At this point, the seeding decisions seem to be more complicated than can be explained by a simple formula.
The big benefit from projecting bids/seeds relative to other bracketologists ought to come EARLIER in the season, rather than LATER. In fact, RPIFORECAST is one of the best at predicting seeds in December/January and February. We have archived all of the major bracketologists' predictions this season and will be determining who were the best and worst EARLY in the season.
Anyway, thanks for visiting, enjoy the tournament, and look for some more exciting things next season!
As for seeds, there IS something to be ashamed of. Quite simply, the seed predictions stunk! In the name of objectivity, we wanted to avoid tweaking the seeds and let the formulas do all the work. However, something obviously needs to be done. The plan for next season is probably to abandon the formulas for seeding - or at least to modify them to allow for some "human analysis". We'll stick with the at-large formulas and figure out a better way to seed the teams. At this point, the seeding decisions seem to be more complicated than can be explained by a simple formula.
The big benefit from projecting bids/seeds relative to other bracketologists ought to come EARLIER in the season, rather than LATER. In fact, RPIFORECAST is one of the best at predicting seeds in December/January and February. We have archived all of the major bracketologists' predictions this season and will be determining who were the best and worst EARLY in the season.
Anyway, thanks for visiting, enjoy the tournament, and look for some more exciting things next season!
Monday, February 21, 2011
Bracket Predictions
I've decided to switch up the at-large and seeding formulas a bit. I had been using an equation that includes conference affiliation and representation on the selection committee. However, just today, I switched to one of the models which does not take these into account. This was mainly because of the problem with the MWC teams seeds (BYU, SDSU, etc). Because the MWC has never been this good, it may not make sense to assume that the same "bias" would exist against them this season. Anyway, BYU immediately jumped to a 2 seed and SDSU to a 5 seed (the highest 5 seed).
http://www.rpiforecast.com/bracket.html
http://www.rpiforecast.com/bracket.html
Tuesday, November 30, 2010
Tourney Projections: A few new features
I added the following features with regards to NCAA tournament bracket projections:
1. ON the main bracket page (www.rpiforecast.com/bracket.html), I added more stats: Current and Expected RPI, Expected OOC RPI, Current and Expected Records, and Current and Expected Conference Records
2. The daily projected tournament seed can now be found on the individual team pages (for example, see Duke: www.rpiforecast.com/teams/Duke.html)
3. I've added a graph on the individual team pages below the other two graphs which tracks the history of projected seeds for each team. You will be hard pressed to find others willing to archive the history of their projections.
Next on the to-do list is BracketBusters and Conference Tournaments.
1. ON the main bracket page (www.rpiforecast.com/bracket.html), I added more stats: Current and Expected RPI, Expected OOC RPI, Current and Expected Records, and Current and Expected Conference Records
2. The daily projected tournament seed can now be found on the individual team pages (for example, see Duke: www.rpiforecast.com/teams/Duke.html)
3. I've added a graph on the individual team pages below the other two graphs which tracks the history of projected seeds for each team. You will be hard pressed to find others willing to archive the history of their projections.
Next on the to-do list is BracketBusters and Conference Tournaments.
Wednesday, November 24, 2010
New Updated Bracket predictions (Daily!)
Based on the new updated "Dance Card" formulas from Jay Coleman, I have started making daily predictions of the field of 68 along with the seeds. A great thing about the methodology is that the factors that determine the at-large bids and the seeds are similar but there are subtle differences. The new model only missed one team from the field and did as well as pretty much anybody at picking the actual seeds. I will be keeping track of my predictions as well as those of the other major bracketologists through the course of the season. After the season is over, I'll present results. If the past is any indicator, my predictions should do especially well early in the season compared to the "human predictions".
Find the predictions here:
http://www.rpiforecast.com/bracket.html
Find the predictions here:
http://www.rpiforecast.com/bracket.html
Live-RPI.com - Minute by Minute RPI Updates - Free!
You may have noticed a brand new feature this season: live-rpi.com . This new website is for those who don't want to wait until the next morning (or even 5 minutes) to see what the current RPI is. As games finish, the RPI is automatically updated and the page should refresh. If it doesn't, simply click on the Live-RPI.com banner and it should refresh. From about 6 am EST to around 1pm, there are no updates unless games are being played. There is also a section on conference RPI which is updated at the same time.
As always, this is free!
As always, this is free!
Sunday, March 14, 2010
Brackets!
How'd we do in projecting the final bracket? Not quite as well as previous years. This is disappointing because in past years, the tournament projections have been more accurate than the vast majority of the other prognosticators - especially from November through February. The bracket forecasts are based on Jay Coleman's OLD "Dance Card Formula". This formula was estimated quite a few years ago to model the behavior of the selection committee. Inevitably, the selection committe changes its behavior over time, so maybe this is not a huge surprise.
The good news is that Jay Coleman has just published a new version of his model. In fact, this new version predicted all but one of the at large bids - and the team missed (Florida versus Miss. St.) were ranked right next to each other and had very similar scores. For next season, we will use the improved updated formula and will also start projecting seeds instead of simply ranking them in order of probability of an at-large bid. Jay Coleman and his co-authors also have a new model that predicts seeds which will be used on this site.
Most pundits project brackets using a "what if the season ended today" framework. The approach taken on this site is to project what the field will look like on Selection Sunday. The advantage of combining the simulations on RPIforecast.com and the Dance Card formula is twofold: (1) The actual forecasts of RPI and records which feed into the formula are much more accurate than using the current RPI and record and (2) The Dance Card Formula (especially the new version) is objective and unbiased and does a remarkable job at predicting the field.
The good news is that Jay Coleman has just published a new version of his model. In fact, this new version predicted all but one of the at large bids - and the team missed (Florida versus Miss. St.) were ranked right next to each other and had very similar scores. For next season, we will use the improved updated formula and will also start projecting seeds instead of simply ranking them in order of probability of an at-large bid. Jay Coleman and his co-authors also have a new model that predicts seeds which will be used on this site.
Most pundits project brackets using a "what if the season ended today" framework. The approach taken on this site is to project what the field will look like on Selection Sunday. The advantage of combining the simulations on RPIforecast.com and the Dance Card formula is twofold: (1) The actual forecasts of RPI and records which feed into the formula are much more accurate than using the current RPI and record and (2) The Dance Card Formula (especially the new version) is objective and unbiased and does a remarkable job at predicting the field.
Subscribe to:
Posts (Atom)