| # | School | Team | Rec. | |
|---|---|---|---|---|
| 1 | Brown University | Bears | 10–0 | |
| 2 | Boston College | Eagles | 7–3 | |
| 3 | Boston University | Terriers | 5–5 | |
| 4 | University of Rhode Island | Rams | 4–6 | |
| 5 | University of South Florida | Bulls | 5–5 | |
| 6 | Tufts University | Jumbos | 4–6 | |
| 7 | Massachusetts Institute of Technology | Engineers | 3–6 | |
| 8 | Northeastern University | Huskies | 1–8 |
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 13,135 team race matches sailed before 2019-03-24, using the line-ups that actually raced. It called 26 of 39 matches (67%) with a log-loss of 0.614 (a coin flip scores 0.693), so the event went poorly for the forecast. Orderliness −0.33 ± 0.32: an upset-heavy event, more orderly than 18% 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 | Brown University | 8.22 | 11.22 | 10–0 | 5.7 | ≥+3.00 | 8.5 | <1% |
| 4 | University of Rhode Island | 6.63 | 7.72 | 4–6 | 2.1 | +1.09 | 1.6 | 12% |
| 6 | Tufts University | 7.12 | 7.26 | 4–6 | 3.7 | +0.14 | 0.0 | 56% |
| 5 | University of South Florida | 7.98 | 7.55 | 5–5 | 5.9 | −0.43 | 0.3 | 84% |
| 2 | Boston College | 9.22 | 8.68 | 7–3 | 7.9 | −0.53 | 0.4 | 87% |
| 8 | Northeastern University | 6.20 | 5.60 | 1–8 | 1.6 | −0.60 | 0.3 | 85% |
| 3 | Boston University | 8.71 | 7.73 | 5–5 | 6.9 | −0.98 | 1.4 | 96% |
| 7 | Massachusetts Institute of Technology | 8.08 | 6.87 | 3–6 | 5.2 | −1.22 | 1.9 | 98% |
| Skipper | School | Value | Perf. | Record | Exp. wins | Δ | Surprise (bits) | P(this good or better) |
|---|---|---|---|---|---|---|---|---|
| Rachel Foster | Brown University | 2.51 | 5.51 | 10–0 | 5.7 | ≥+3.00 | 8.5 | <1% |
| Sophie Hibben | Brown University | 2.92 | 5.92 | 10–0 | 5.7 | ≥+3.00 | 8.5 | <1% |
| Olivia Belda | Brown University | 2.40 | 5.40 | 10–0 | 5.7 | ≥+3.00 | 8.5 | <1% |
| Abbie Carlson | Tufts University | 1.83 | 1.97 | 4–6 | 3.7 | +0.14 | 0.0 | 56% |
| Isabella Loosbrock | Boston College | 3.15 | 2.62 | 7–3 | 7.9 | −0.53 | 0.4 | 87% |
| Carolyn Corbet | Northeastern University | 2.49 | 1.88 | 1–8 | 1.6 | −0.60 | 0.3 | 85% |
| Allison Cahn | Boston University | 2.60 | 1.61 | 5–5 | 6.9 | −0.98 | 1.4 | 96% |
| Grace Mooradian | Boston University | 2.80 | 1.82 | 5–5 | 6.9 | −0.98 | 1.4 | 96% |
| Annie Hughes | Massachusetts Institute of Technology | 2.99 | 1.77 | 3–6 | 5.2 | −1.22 | 1.9 | 98% |
Probability the model gave the side that went on to win. Red bars are upsets (the winner was given under 50%).
| Team | Rec. | Bears | Eagles | Terriers | Rams | Bulls | Jumbos | Engineers | Huskies | |
|---|---|---|---|---|---|---|---|---|---|---|
| Brown University Bears | 7–0 | ✕ | W | W | W | W | W | W | W | |
| Boston College Eagles | 5–2 | L | ✕ | L | W | W | W | W | W | |
| Boston University Terriers | 4–3 | L | W | ✕ | L | W | L | W | W | |
| University of Rhode Island Rams | 4–3 | L | L | W | ✕ | L | W | W | W | |
| University of South Florida Bulls | 2–5 | L | L | L | W | ✕ | L | L | W | |
| Tufts University Jumbos | 3–4 | L | L | W | L | W | ✕ | L | W | |
| Massachusetts Institute of Technology Engineers | 3–4 | L | L | L | L | W | W | ✕ | W | |
| Northeastern University Huskies | 0–7 | L | L | L | L | L | L | L | ✕ |
| Team | Rec. | Bears | Eagles | Terriers | Rams | Bulls | Jumbos | Engineers | Huskies | |
|---|---|---|---|---|---|---|---|---|---|---|
| Brown University Bears | 3–0 | ✕ | W | W | W | – | – | – | – | |
| Boston College Eagles | 2–1 | L | ✕ | W | W | – | – | – | – | |
| Boston University Terriers | 1–2 | L | L | ✕ | W | – | – | – | – | |
| University of Rhode Island Rams | 0–3 | L | L | L | ✕ | – | – | – | – | |
| University of South Florida Bulls | 3–0 | – | – | – | – | ✕ | W | W | W | |
| Tufts University Jumbos | 1–2 | – | – | – | – | L | ✕ | W | L | |
| Massachusetts Institute of Technology Engineers | 0–2 | – | – | – | – | L | L | ✕ | – | |
| Northeastern University Huskies | 1–1 | – | – | – | – | L | W | – | ✕ |
| # | Winner | Loser | Pos. | ||||
|---|---|---|---|---|---|---|---|
| 1 | Engineers | 1-3-6 | def. | Huskies | 2-4-5 | ||
| 2 | Jumbos | 1-3-5 | def. | Terriers | 2-4-6 | ||
| 3 | Bears | 1-4-5 | def. | Rams | 2-3-6 | ||
| 4 | Eagles | 1-2-6 | def. | Bulls | 3-4-5 | ||
| 5 | Terriers | 1-2-6 | def. | Engineers | 3-4-5 | ||
| 6 | Bears | 1-2-4 | def. | Huskies | 3-5-6 | ||
| 7 | Jumbos | 1-2-6 | def. | Bulls | 3-4-5 | ||
| 8 | Eagles | 2-3-4 | def. | Rams | 1-5-6 | ||
| 9 | Bears | 1-2-6 | def. | Terriers | 3-4-5 | ||
| 10 | Engineers | 1-3-5 | def. | Bulls | 2-4-6 | ||
| 11 | Rams | 2-3-5 | def. | Huskies | 1-4-6 | ||
| 12 | Eagles | 1-2-4 | def. | Jumbos | 3-5-6 | ||
| 13 | Bears | 2-3-4 | def. | Bulls | 1-5-6 | ||
| 14 | Rams | 1-2-5 | def. | Terriers | 3-4-6 | ||
| 15 | Engineers | 1-3-4 | def. | Jumbos | 2-5-6 | ||
| 16 | Eagles | 1-2-4 | def. | Huskies | 3-5-6 | ||
| 17 | Bulls | 1-2-4 | def. | Rams | 3-5-6 | ||
| 18 | Bears | 1-2-6 | def. | Jumbos | 3-4-5 | ||
| 19 | Terriers | 1-2-5 | def. | Huskies | 3-4-6 | ||
| 20 | Eagles | 1-2-5 | def. | Engineers | 3-4-6 | ||
| 21 | Rams | 1-2-3 | def. | Jumbos | 4-5-6 | ||
| 22 | Bulls | 1-2-5 | def. | Huskies | 3-4-6 | ||
| 23 | Bears | 1-3-5 | def. | Engineers | 2-4-6 | ||
| 24 | Terriers | 1-3-6 | def. | Eagles | 2-4-5 | ||
| 25 | Jumbos | 1-2-6 | def. | Huskies | 3-4-5 | ||
| 26 | Rams | 2-3-4 | def. | Engineers | 1-5-6 | ||
| 27 | Terriers | 2-3-4 | def. | Bulls | 1-5-6 | ||
| 28 | Bears | 1-2-5 | def. | Eagles | 3-4-6 | ||
| 29 | Bulls | 2-3-4 | def. | Huskies | 1-5-6 | ||
| 30 | Bulls | 1-3-5 | def. | Jumbos | 2-4-6 | ||
| 31 | Bulls | 1-2-4 | def. | Engineers | 3-5-6 | ||
| 32 | Huskies | 1-2-4 | def. | Jumbos | 3-5-6 | ||
| 33 | Jumbos | 2-3-4 | def. | Engineers | 1-5-6 | ||
| 34 | Bears | 1-2-5 | def. | Rams | 3-4-6 | ||
| 35 | Eagles | 1-3-6 | def. | Terriers | 2-4-5 | ||
| 36 | Eagles | 1-2-6 | def. | Rams | 3-4-5 | ||
| 37 | Bears | 1-2-5 | def. | Terriers | 3-4-6 | ||
| 38 | Terriers | 2-3-4 | def. | Rams | 1-5-6 | ||
| 39 | Bears | 1-2-5 | def. | Eagles | 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 ±0.05 means a rating gap counts about 4% 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.