| # | School | Team | Rec. | |
|---|---|---|---|---|
| 1 |  |
Roger Williams University | Hawks | 6–0 |
| 2 |  |
Boston University | Terriers | 5–1 |
| 3 |  |
Tufts University | Jumbos | 3–3 |
| 4 |  |
Brown University | Bears | 2–3 |
| 4 |  |
Connecticut College | Camels | 2–3 |
| 6 |  |
U. S. Coast Guard Academy | Bears | 2–4 |
| 6 |  |
University of Rhode Island | Rams | 2–4 |
| 8 |  |
Yale University | Bulldogs | 1–5 |
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 12,061 team race matches sailed before 2019-03-02, using the line-ups that actually raced. It called 18 of 23 matches (78%) with a log-loss of 0.498 (a coin flip scores 0.693), so the event went about as expected for the forecast. Orderliness −0.24 ± 0.41: a typical event, more orderly than 21% 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 | Roger Williams University | 10.32 | 13.32 | 6–0 | 5.1 | ≥+3.00 | 1.4 | 36% |
| 6 | University of Rhode Island | 6.32 | 7.53 | 2–4 | 1.1 | +1.21 | 0.8 | 27% |
| 8 | Yale University | 5.43 | 6.60 | 1–5 | 0.5 | +1.16 | 0.5 | 41% |
| 2 | Boston University | 9.45 | 10.49 | 5–1 | 4.1 | +1.04 | 0.6 | 36% |
| 4 | Connecticut College | 8.67 | 8.39 | 2–3 | 2.3 | −0.27 | 0.0 | 78% |
| 4 | Brown University | 8.08 | 7.44 | 2–3 | 2.4 | −0.64 | 0.2 | 89% |
| 3 | Tufts University | 8.82 | 7.85 | 3–3 | 4.0 | −0.97 | 0.7 | 94% |
| 6 | U. S. Coast Guard Academy | 9.19 | 7.74 | 2–4 | 3.5 | −1.44 | 1.5 | 98% |
| Skipper | School | Value | Perf. | Record | Exp. wins | Δ | Surprise (bits) | P(this good or better) |
|---|---|---|---|---|---|---|---|---|
| Conner Harding | Roger Williams University | 3.86 | 6.86 | 6–0 | 5.1 | ≥+3.00 | 1.4 | 36% |
| Spencer Cartwright | Roger Williams University | 3.15 | 6.15 | 6–0 | 5.1 | ≥+3.00 | 1.4 | 36% |
| Aidan Naughton | University of Rhode Island | 2.46 | 3.67 | 2–4 | 1.1 | +1.21 | 0.8 | 27% |
| Martin Tipton | Yale University | 1.42 | 2.58 | 1–5 | 0.5 | +1.16 | 0.5 | 41% |
| Sam Tobin | Yale University | 1.68 | 2.85 | 1–5 | 0.5 | +1.16 | 0.5 | 41% |
| Javier De Urdanibia Panos | Boston University | 3.06 | 4.11 | 5–1 | 4.1 | +1.04 | 0.6 | 36% |
| Garrett Connelly | University of Rhode Island | 1.38 | 1.58 | 1–4 | 0.9 | +0.20 | 0.0 | 74% |
| Thomas Whittemore | Connecticut College | 2.42 | 2.48 | 2–2 | 2.0 | +0.06 | 0.0 | 69% |
| Charlie Hibben | Tufts University | 2.83 | 1.86 | 3–3 | 4.0 | −0.97 | 0.7 | 94% |
| Samuel Shea | Tufts University | 2.66 | 1.69 | 3–3 | 4.0 | −0.97 | 0.7 | 94% |
| Gage Schoenherr | U. S. Coast Guard Academy | 3.08 | 1.63 | 2–4 | 3.5 | −1.44 | 1.5 | 98% |
Probability the model gave the side that went on to win. Red bars are upsets (the winner was given under 50%).
| Team | Rec. | Hawks | Terriers | Jumbos | Bears | Camels | Bears | Rams | Bulldogs | |
|---|---|---|---|---|---|---|---|---|---|---|
| Roger Williams University Hawks | 6–0 | ✕ | W | – | W | W | W | W | W |
| Boston University Terriers | 5–1 | L | ✕ | W | – | W | W | W | W |
| Tufts University Jumbos | 3–3 | – | L | ✕ | W | W | L | L | W |
| Brown University Bears | 2–3 | L | – | L | ✕ | – | W | L | W |
| Connecticut College Camels | 2–3 | L | L | L | – | ✕ | W | W | – |
| U. S. Coast Guard Academy Bears | 2–4 | L | L | W | L | L | ✕ | – | W |
| University of Rhode Island Rams | 2–4 | L | L | W | W | L | – | ✕ | L |
| Yale University Bulldogs | 1–5 | L | L | L | L | – | L | W | ✕ |
| # | Winner | Loser | Pos. | ||||
|---|---|---|---|---|---|---|---|
| 1 | |
Hawks | 1-2-4 | def. | |
Bears | 3-5-6 |
| 2 | |
Jumbos | 1-2-4 | def. | |
Camels | 3-5-6 |
| 3 | |
Terriers | 1-2-4 | def. | |
Rams | 3-5-6 |
| 4 | |
Bears | 1-2-5 | def. | |
Bulldogs | 3-4-6 |
| 5 | |
Camels | 2-3-4 | def. | |
Bears | 1-5-6 |
| 6 | |
Hawks | 1-2-5 | def. | |
Terriers | 3-4-6 |
| 7 | |
Jumbos | 1-2-5 | def. | |
Bulldogs | 3-4-6 |
| 8 | |
Rams | 1-2-3 | def. | |
Bears | 4-5-6 |
| 9 | |
Terriers | 1-2-5 | def. | |
Camels | 3-4-6 |
| 10 | |
Bears | 1-2-5 | def. | |
Bulldogs | 3-4-6 |
| 11 | |
Hawks | 1-2-5 | def. | |
Rams | 3-4-6 |
| 12 | |
Jumbos | 1-2-6 | def. | |
Bears | 3-4-5 |
| 13 | |
Terriers | 1-2-3 | def. | |
Bulldogs | 4-5-6 |
| 14 | |
Camels | 1-2-5 | def. | |
Rams | 3-4-6 |
| 15 | |
Bears | 1-2-3 | def. | |
Jumbos | 4-5-6 |
| 16 | |
Hawks | 1-4-5 | def. | |
Bears | 2-3-6 |
| 17 | |
Bulldogs | 1-2-5 | def. | |
Rams | 3-4-6 |
| 18 | |
Terriers | 1-2-5 | def. | |
Jumbos | 3-4-6 |
| 19 | |
Hawks | 1-2-5 | def. | |
Camels | 3-4-6 |
| 20 | |
Bears | 1-2-6 | def. | |
Bears | 3-4-5 |
| 21 | |
Rams | 1-3-4 | def. | |
Jumbos | 2-5-6 |
| 22 | |
Hawks | 1-2-6 | def. | |
Bulldogs | 3-4-5 |
| 23 | |
Terriers | 1-2-5 | def. | |
Bears | 3-4-6 |
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 ±0.06 means a rating gap counts about 5% 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.
