| # | School | Team | Rec. | |
|---|---|---|---|---|
| 1 |  |
Boston College | Eagles | 9–1 |
| 2 |  |
Boston University | Terriers | 7–3 |
| 3 |  |
U. S. Coast Guard Academy | Bears | 6–4 |
| 4 |  |
Roger Williams University | Hawks | 5–5 |
| 5 |  |
Bowdoin College | Polar Bears | 3–7 |
| 6 |  |
Harvard University | Crimson | 0–10 |
Each side is the sum of its three boats (the skipper's fleet rating times 0.72 plus a team race offset learned from their past matches, plus the crew's offset and a small experience term) plus the school's team race strength and a home-water edge for the host. The win probability is a logistic function of the difference. The forecast was made before the event: the model was refitted on every match sailed before the first day, with fleet ratings as of the week before.
Fitted on the 8,444 team race matches sailed before 2017-03-26, using the line-ups that actually raced. It called 26 of 30 matches (87%) with a log-loss of 0.433 (a coin flip scores 0.693), so the event went well for the forecast. Orderliness +0.19 ± 0.34: a typical event, more orderly than 66% of college team race events (temperature of the forecast log-odds that best fits the results, relative to the league average; nothing about the field, venue or wind predicts it, see the Weather tab). vs forecast is a team's wins minus the wins the model expected from the matches it sailed: positive means it beat its rating.
For each side, the performance strength is the value that would have made its record least surprising: the strength at which the model's expected wins over exactly these opponents equal the actual wins, with every opponent fixed at its pre-event strength. For a skipper, the same shift is applied only to their boat in the matches they sailed, with team-mates and opponents fixed; team-mates who sailed every match together therefore get the same number. Surprise is in bits: -log2 of the probability of the record at the pre-event strength minus the same at the performance strength. P(this good or better) treats matches as independent coin flips at the model's pre-event probabilities, so it ignores form within the day; read it as a rough guide.
Pre-event strength against the strength that would have made each record least surprising, everything else fixed. Δ is in the model's logit units, the same scale as the boat values above (a side is three boats plus the school term); green is a clear over-performance, red a clear under-performance. Skippers need three or more matches.
| Place | School | Strength | Perf. | Record | Exp. wins | Δ | Surprise (bits) | P(this good or better) |
|---|---|---|---|---|---|---|---|---|
| 2 | Boston University | 7.59 | 8.38 | 7–3 | 5.8 | +0.79 | 0.7 | 27% |
| 1 | Boston College | 8.49 | 9.27 | 9–1 | 8.1 | +0.78 | 0.4 | 41% |
| 3 | U. S. Coast Guard Academy | 6.98 | 7.64 | 6–4 | 4.7 | +0.66 | 0.6 | 28% |
| 5 | Bowdoin College | 6.15 | 6.51 | 3–7 | 2.4 | +0.36 | 0.1 | 46% |
| 4 | Roger Williams University | 8.06 | 6.90 | 5–5 | 7.2 | −1.16 | 1.9 | 98% |
| 6 | Harvard University | 5.73 | 2.73 | 0–10 | 1.7 | ≤−3.00 | 2.7 | >99% |
| Skipper | School | Value | Perf. | Record | Exp. wins | Δ | Surprise (bits) | P(this good or better) |
|---|---|---|---|---|---|---|---|---|
| Anna Weis | Boston University | 2.43 | 3.22 | 7–3 | 5.8 | +0.79 | 0.7 | 27% |
| Alex Moreno | Boston University | 2.73 | 3.52 | 7–3 | 5.8 | +0.79 | 0.7 | 27% |
| Jacob Martz | Boston College | 2.52 | 3.30 | 9–1 | 8.1 | +0.78 | 0.4 | 41% |
| August Sturm | U. S. Coast Guard Academy | 3.09 | 3.75 | 6–4 | 4.7 | +0.66 | 0.6 | 28% |
| Michael Kann | Bowdoin College | 1.55 | 1.91 | 3–7 | 2.4 | +0.36 | 0.1 | 46% |
| Chester Jacobs | Bowdoin College | 2.58 | 2.94 | 3–7 | 2.4 | +0.36 | 0.1 | 46% |
| Louis Frumer | Bowdoin College | 1.34 | 1.70 | 3–7 | 2.4 | +0.36 | 0.1 | 46% |
| Janel Decurtis | Roger Williams University | 2.32 | 1.15 | 5–5 | 7.2 | −1.16 | 1.9 | 98% |
| Andrew Puopolo | Harvard University | 2.21 | -0.79 | 0–10 | 1.7 | ≤−3.00 | 2.7 | >99% |
| Sofia Marie Mascia | Harvard University | 1.65 | -1.35 | 0–10 | 1.7 | ≤−3.00 | 2.7 | >99% |
| Catherine Kerner | Harvard University | 1.44 | -1.56 | 0–10 | 1.7 | ≤−3.00 | 2.7 | >99% |
Probability the model gave the side that went on to win. Red bars are upsets (the winner was given under 50%).
| Team | Rec. | Eagles | Terriers | Bears | Hawks | Bears | Crimson | |
|---|---|---|---|---|---|---|---|---|
| Boston College Eagles | 5–0 | ✕ | W | W | W | W | W |
| Boston University Terriers | 3–2 | L | ✕ | W | L | W | W |
| U. S. Coast Guard Academy Bears | 3–2 | L | L | ✕ | W | W | W |
| Roger Williams University Hawks | 3–2 | L | W | L | ✕ | W | W |
| Bowdoin College Polar Bears | 1–4 | L | L | L | L | ✕ | W |
| Harvard University Crimson | 0–5 | L | L | L | L | L | ✕ |
| Team | Rec. | Eagles | Terriers | Bears | Hawks | Bears | Crimson | |
|---|---|---|---|---|---|---|---|---|
| Boston College Eagles | 4–1 | ✕ | L | W | W | W | W |
| Boston University Terriers | 4–1 | W | ✕ | W | L | W | W |
| U. S. Coast Guard Academy Bears | 3–2 | L | L | ✕ | W | W | W |
| Roger Williams University Hawks | 2–3 | L | W | L | ✕ | L | W |
| Bowdoin College Polar Bears | 2–3 | L | L | L | W | ✕ | W |
| Harvard University Crimson | 0–5 | L | L | L | L | L | ✕ |
| # | Winner | Loser | Pos. | ||||
|---|---|---|---|---|---|---|---|
| 1 | |
Bears | 1-2-5 | def. | |
Polar Bears | 3-4-6 |
| 2 | |
Terriers | 1-2-6 | def. | |
Crimson | 3-4-5 |
| 3 | |
Eagles | 1-2-3 | def. | |
Hawks | 4-5-6 |
| 4 | |
Terriers | 1-3-6 | def. | |
Polar Bears | 2-4-5 |
| 5 | |
Bears | 1-2-5 | def. | |
Hawks | 3-4-6 |
| 6 | |
Eagles | 1-2-5 | def. | |
Crimson | 3-4-6 |
| 7 | |
Hawks | 1-2-4 | def. | |
Terriers | 3-5-6 |
| 8 | |
Polar Bears | 1-2-3 | def. | |
Crimson | 4-5-6 |
| 9 | |
Eagles | 1-2-4 | def. | |
Bears | 3-5-6 |
| 10 | |
Hawks | 2-3-4 | def. | |
Crimson | 1-5-6 |
| 11 | |
Terriers | 2-3-4 | def. | |
Bears | 1-5-6 |
| 12 | |
Eagles | 1-2-3 | def. | |
Polar Bears | 4-5-6 |
| 13 | |
Bears | 2-3-5 | def. | |
Crimson | 1-4-6 |
| 14 | |
Hawks | 1-2-4 | def. | |
Polar Bears | 3-5-6 |
| 15 | |
Eagles | 1-3-5 | def. | |
Terriers | 2-4-6 |
| 16 | |
Terriers | 1-2-6 | def. | |
Polar Bears | 3-4-5 |
| 17 | |
Eagles | 1-3-5 | def. | |
Bears | 2-4-6 |
| 18 | |
Hawks | 1-2-4 | def. | |
Crimson | 3-5-6 |
| 19 | |
Eagles | 1-3-5 | def. | |
Polar Bears | 2-4-6 |
| 20 | |
Terriers | 1-2-6 | def. | |
Crimson | 3-4-5 |
| 21 | |
Bears | 1-2-4 | def. | |
Hawks | 3-5-6 |
| 22 | |
Eagles | 1-2-4 | def. | |
Crimson | 3-5-6 |
| 23 | |
Bears | 1-3-5 | def. | |
Polar Bears | 2-4-6 |
| 24 | |
Hawks | 2-3-4 | def. | |
Terriers | 1-5-6 |
| 25 | |
Bears | 1-2-6 | def. | |
Crimson | 3-4-5 |
| 26 | |
Terriers | 1-2-5 | def. | |
Eagles | 3-4-6 |
| 27 | |
Polar Bears | 2-3-4 | def. | |
Hawks | 1-5-6 |
| 28 | |
Terriers | 2-3-4 | def. | |
Bears | 1-5-6 |
| 29 | |
Polar Bears | 1-3-5 | def. | |
Crimson | 2-4-6 |
| 30 | |
Eagles | 1-2-6 | def. | |
Hawks | 3-4-5 |
| School | Team | Skippers | Crew | |
|---|---|---|---|---|
|
Boston College | Eagles | Jacob Martz '17 Peter Lynn '19 Scott Rasmussen '20 |
Lauren Seigel '20 Katharine Bowman '20 Tara Ferraris '19 |
|
Boston University | Terriers | Alex Moreno '19 Anna Weis '20 Charles Welsh '18 John Wetzel '20 |
Emily Walker '19 Lily Lichtenstein '18 Jacqueline Farnsworth '17 |
|
U. S. Coast Guard Academy | Bears | August Sturm '19 Caelan Juckniess '20 Liam Ballantyne '19 |
Rebecca Edmonds '19 Sarah Smith '20 Anna Maria Vaccaro '19 |
|
Roger Williams University | Hawks | Janel Decurtis '18 Kelsey Shakin '19 Maia Agerup '20 |
Peter Forsberg '19 Megan Roach '18 Ariana Smaldone '20 |
|
Bowdoin College | Polar Bears | Chester Jacobs '17 Louis Frumer '18 Michael Kann '19 |
Caitlin Tardio '19 Emily Gonzalez '20 Eve Allen '19 |
|
Harvard University | Crimson | Andrew Puopolo '19 Catherine Kerner '20 Sofia Marie Mascia '20 |
Lena Episalla '19 Juan Crestanello '20 Victoria Marquez '20 |
Orderliness is how tightly a fleet race’s finishing order follows the pre-regatta ratings, relative to a typical event (0): positive is the favourites’ day, negative the underdogs’. A value of ±0.02 means a rating gap counts about 2% more than on a typical day. This event is not a fleet race the rating model scores, so there is no actual value for it: this is what this venue’s fleet racing history says about the breeze on the day, read off the chart at the star. How this is estimated · compare venues.
Short write-ups of what the ratings and results show, with the numbers and how they were computed.
