| # | School | Team | Rec. | |
|---|---|---|---|---|
| 1 |  |
Boston College | Eagles | 5–0 |
| 2 |  |
Yale University | Bulldogs | 4–1 |
| 3 |  |
Brown University | Bears | 3–2 |
| 4 |  |
Roger Williams University | Hawks | 2–3 |
| 5 |  |
Boston University | Terriers | 1–4 |
| 6 |  |
Tufts University | Jumbos | 0–5 |
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 9,158 team race matches sailed before 2017-10-14, using the line-ups that actually raced. It called 13 of 15 matches (87%) with a log-loss of 0.374 (a coin flip scores 0.693), so the event went well for the forecast. Orderliness +0.51 ± 0.59: a typical event, more orderly than 94% 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) |
|---|---|---|---|---|---|---|---|---|
| 1 | Boston College | 9.48 | 12.48 | 5–0 | 4.0 | ≥+3.00 | 1.5 | 32% |
| 2 | Yale University | 8.41 | 9.85 | 4–1 | 2.7 | +1.44 | 1.2 | 22% |
| 3 | Brown University | 8.23 | 8.69 | 3–2 | 2.5 | +0.46 | 0.2 | 51% |
| 4 | Roger Williams University | 8.38 | 7.50 | 2–3 | 2.8 | −0.88 | 0.5 | 91% |
| 5 | Boston University | 8.40 | 5.84 | 1–4 | 2.8 | −2.56 | 2.8 | >99% |
| 6 | Tufts University | 4.87 | 1.87 | 0–5 | 0.1 | ≤−3.00 | 0.2 | >99% |
| Skipper | School | Value | Perf. | Record | Exp. wins | Δ | Surprise (bits) | P(this good or better) |
|---|---|---|---|---|---|---|---|---|
| Drake Lyon | Boston College | 2.95 | 5.95 | 5–0 | 4.0 | ≥+3.00 | 1.5 | 32% |
| Dylan Dimarchi | Yale University | 3.04 | 4.48 | 4–1 | 2.7 | +1.44 | 1.2 | 22% |
| Franco Bilik | Brown University | 2.78 | 3.24 | 3–2 | 2.5 | +0.46 | 0.2 | 51% |
| Spencer Cartwright | Roger Williams University | 2.59 | 1.71 | 2–3 | 2.8 | −0.88 | 0.5 | 91% |
| Andrew Savage | Tufts University | 1.95 | -1.05 | 0–5 | 0.1 | ≤−3.00 | 0.2 | >99% |
| John Duncan | Tufts University | 1.78 | -1.22 | 0–5 | 0.1 | ≤−3.00 | 0.2 | >99% |
| Evan Robison | Tufts University | 0.93 | -2.07 | 0–5 | 0.1 | ≤−3.00 | 0.2 | >99% |
Probability the model gave the side that went on to win. Red bars are upsets (the winner was given under 50%).
| Rd | # | Winner | Loser | P(winner) | |
|---|---|---|---|---|---|
| 1 | 1 | Brown University | Roger Williams University | 43% | upset |
| 1 | 2 | Boston University | Tufts University | 97% | |
| 1 | 3 | Boston College | Yale University | 77% | |
| 1 | 4 | Brown University | Boston University | 44% | upset |
| 1 | 5 | Yale University | Roger Williams University | 50% | |
| 1 | 6 | Boston College | Tufts University | 99% | |
| 1 | 7 | Yale University | Boston University | 51% | |
| 1 | 8 | Brown University | Tufts University | 97% | |
| 1 | 9 | Boston College | Roger Williams University | 75% | |
| 1 | 10 | Yale University | Tufts University | 97% | |
| 1 | 11 | Roger Williams University | Boston University | 50% | |
| 1 | 12 | Boston College | Brown University | 76% | |
| 1 | 13 | Roger Williams University | Tufts University | 97% | |
| 1 | 14 | Yale University | Brown University | 53% | |
| 1 | 15 | Boston College | Boston University | 75% |
| Team | Rec. | Eagles | Bulldogs | Bears | Hawks | Terriers | Jumbos | |
|---|---|---|---|---|---|---|---|---|
| Boston College Eagles | 5–0 | ✕ | W | W | W | W | W |
| Yale University Bulldogs | 4–1 | L | ✕ | W | W | W | W |
| Brown University Bears | 3–2 | L | L | ✕ | W | W | W |
| Roger Williams University Hawks | 2–3 | L | L | L | ✕ | W | W |
| Boston University Terriers | 1–4 | L | L | L | L | ✕ | W |
| Tufts University Jumbos | 0–5 | L | L | L | L | L | ✕ |
| # | Winner | Loser | Pos. | ||||
|---|---|---|---|---|---|---|---|
| 1 | |
Bears | 1-2-3 | def. | |
Hawks | 4-5-6 |
| 2 | |
Terriers | 1-2-6 | def. | |
Jumbos | 3-4-5 |
| 3 | |
Eagles | 1-2-5 | def. | |
Bulldogs | 3-4-6 |
| 4 | |
Bears | 1-2-3 | def. | |
Terriers | 4-5-6 |
| 5 | |
Bulldogs | 1-2-4 | def. | |
Hawks | 3-5-6 |
| 6 | |
Eagles | 1-2-4 | def. | |
Jumbos | 3-5-6 |
| 7 | |
Bulldogs | 1-3-4 | def. | |
Terriers | 2-5-6 |
| 8 | |
Bears | 1-2-3 | def. | |
Jumbos | 4-5-6 |
| 9 | |
Eagles | 1-2-4 | def. | |
Hawks | 3-5-6 |
| 10 | |
Bulldogs | 1-2-4 | def. | |
Jumbos | 3-5-6 |
| 11 | |
Hawks | 1-3-6 | def. | |
Terriers | 2-4-5 |
| 12 | |
Eagles | 1-2-3 | def. | |
Bears | 4-5-6 |
| 13 | |
Hawks | 1-2-4 | def. | |
Jumbos | 3-5-6 |
| 14 | |
Bulldogs | 1-2-6 | def. | |
Bears | 3-4-5 |
| 15 | |
Eagles | 1-2-3 | def. | |
Terriers | 4-5-6 |
| School | Team | Skippers | Crew | |
|---|---|---|---|---|
|
Boston College | Eagles | Drake Lyon '18 Scott Rasmussen '20 Thomas Walden '20 |
Katharine Bowman '20 Megan Bamford '18 Lauren Seigel '20 |
|
Yale University | Bulldogs | Christine Klingler '20 Dylan Dimarchi '20 Nicholas Marwell '21 |
Katharina (Kb) Knapp '18 Becca Rose '22 Emery Wallace '21 |
|
Brown University | Bears | Franco Bilik '18 John Mastrandrea '20 Sam Alexander '18 |
Lauren Haller '18 Sawyer Balint '20 Megha Malpani '19 |
|
Roger Williams University | Hawks | Daniel Petrovic '19 Peter Neal '20 Spencer Cartwright '22 |
Tyler Killion '18 Dane Pedersen '19 Henry Stames '18 |
|
Boston University | Terriers | Casey Cabot '21 Kyle Dochoda '21 Michael Sabourin '20 |
Erica Brown '21 Emily Walker '19 Shannon Macdonald '21 |
|
Tufts University | Jumbos | Andrew Savage '19 Evan Robison '21 John Duncan '19 |
Kahler Newsham '19 Marley Hillman '21 Juliana Testa '21 |
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 ±0.07 means a rating gap counts about 6% less 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.
