| # | School | Team | Rec. | |
|---|---|---|---|---|
| 1 | Stanford University | Cardinal | 7–1 | |
| 2 | University of Hawaii | Rainbows | 6–2 | |
| 3 | University of California at Santa Barbara | Gauchos | 5–3 | |
| 4 | Cal Poly University S.L.O. | Mustang | 2–6 | |
| 5 | University of California at Berkeley | Bears | 0–8 |
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 8,954 team race matches sailed before 2017-04-30, using the line-ups that actually raced. It called 18 of 20 matches (90%) with a log-loss of 0.378 (a coin flip scores 0.693), so the event went well for the forecast. Orderliness −0.31 ± 0.39: a typical 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) |
|---|---|---|---|---|---|---|---|---|
| 2 | University of Hawaii | 8.24 | 10.96 | 6–2 | 3.8 | +2.72 | 4.4 | 2% |
| 4 | Cal Poly University S.L.O. | 6.61 | 6.98 | 2–6 | 1.7 | +0.37 | 0.1 | 59% |
| 3 | University of California at Santa Barbara | 9.98 | 8.74 | 5–3 | 5.9 | −1.24 | 0.8 | 96% |
| 1 | Stanford University | 11.83 | 10.47 | 7–1 | 7.7 | −1.36 | 0.7 | 97% |
| 5 | University of California at Berkeley | 5.98 | 2.98 | 0–8 | 0.9 | ≤−3.00 | 1.5 | >99% |
| Skipper | School | Value | Perf. | Record | Exp. wins | Δ | Surprise (bits) | P(this good or better) |
|---|---|---|---|---|---|---|---|---|
| Jeremy Hitchcock | University of Hawaii | 2.48 | 5.48 | 4–0 | 3.5 | ≥+3.00 | 0.7 | 58% |
| Chuck Eaton | University of Hawaii | 3.02 | 5.73 | 6–2 | 3.8 | +2.72 | 4.4 | 2% |
| Ben Brough | Cal Poly University S.L.O. | 2.41 | 2.78 | 2–6 | 1.7 | +0.37 | 0.1 | 59% |
| Joseph Lausten | Cal Poly University S.L.O. | 1.77 | 2.14 | 2–6 | 1.7 | +0.37 | 0.1 | 59% |
| Sterling Henken | University of California at Santa Barbara | 3.08 | 1.84 | 5–3 | 5.9 | −1.24 | 0.8 | 96% |
| Stephen Long | University of California at Santa Barbara | 3.19 | 1.94 | 5–3 | 5.9 | −1.24 | 0.8 | 96% |
| Reinier Eenkema Van Dijk | Stanford University | 3.31 | 1.95 | 7–1 | 7.7 | −1.36 | 0.7 | 97% |
| Andrew Solomon | University of California at Berkeley | 2.54 | -0.46 | 0–8 | 0.9 | ≤−3.00 | 1.5 | >99% |
| Ian Markowitz | University of California at Berkeley | 1.91 | -1.09 | 0–8 | 0.9 | ≤−3.00 | 1.5 | >99% |
| Eric Witte | University of California at Berkeley | 1.48 | -1.52 | 0–8 | 0.9 | ≤−3.00 | 1.5 | >99% |
Probability the model gave the side that went on to win. Red bars are upsets (the winner was given under 50%).
| Team | Rec. | Cardinal | Rainbows | Gauchos | Mustang | Bears | |
|---|---|---|---|---|---|---|---|
| Stanford University Cardinal | 3–1 | ✕ | L | W | W | W | |
| University of Hawaii Rainbows | 4–0 | W | ✕ | W | W | W | |
| University of California at Santa Barbara Gauchos | 2–2 | L | L | ✕ | W | W | |
| Cal Poly University S.L.O. Mustang | 1–3 | L | L | L | ✕ | W | |
| University of California at Berkeley Bears | 0–4 | L | L | L | L | ✕ |
| Team | Rec. | Cardinal | Rainbows | Gauchos | Mustang | Bears | |
|---|---|---|---|---|---|---|---|
| Stanford University Cardinal | 4–0 | ✕ | W | W | W | W | |
| University of Hawaii Rainbows | 2–2 | L | ✕ | L | W | W | |
| University of California at Santa Barbara Gauchos | 3–1 | L | W | ✕ | W | W | |
| Cal Poly University S.L.O. Mustang | 1–3 | L | L | L | ✕ | W | |
| University of California at Berkeley Bears | 0–4 | L | L | L | L | ✕ |
| # | Winner | Loser | Pos. | ||||
|---|---|---|---|---|---|---|---|
| 1 | Rainbows | 2-3-4 | def. | Mustang | 1-5-6 | ||
| 2 | Cardinal | 1-2-4 | def. | Bears | 3-5-6 | ||
| 3 | Gauchos | 1-2-6 | def. | Mustang | 3-4-5 | ||
| 4 | Rainbows | 1-2-6 | def. | Bears | 3-4-5 | ||
| 5 | Cardinal | 1-2-6 | def. | Gauchos | 3-4-5 | ||
| 6 | Mustang | 1-2-4 | def. | Bears | 3-5-6 | ||
| 7 | Rainbows | 1-3-5 | def. | Cardinal | 2-4-6 | ||
| 8 | Gauchos | 1-2-5 | def. | Bears | 3-4-6 | ||
| 9 | Cardinal | 1-2-3 | def. | Mustang | 4-5-6 | ||
| 10 | Rainbows | 1-2-3 | def. | Gauchos | 4-5-6 | ||
| 11 | Rainbows | 1-2-4 | def. | Mustang | 3-5-6 | ||
| 12 | Cardinal | 1-2-6 | def. | Bears | 3-4-5 | ||
| 13 | Gauchos | 1-2-3 | def. | Mustang | 4-5-6 | ||
| 14 | Rainbows | 1-2-5 | def. | Bears | 3-4-6 | ||
| 15 | Cardinal | 1-2-5 | def. | Gauchos | 3-4-6 | ||
| 16 | Mustang | 1-2-6 | def. | Bears | 3-4-5 | ||
| 17 | Cardinal | 1-2-4 | def. | Rainbows | 3-5-6 | ||
| 18 | Gauchos | 1-2-4 | def. | Bears | 3-5-6 | ||
| 19 | Cardinal | 1-2-3 | def. | Mustang | 4-5-6 | ||
| 20 | Gauchos | 1-3-5 | def. | Rainbows | 2-4-6 | ||
| School | Team | Skippers | Crew | |
|---|---|---|---|---|
| Stanford University | Cardinal | Jacob Rosenberg '20 Reinier Eenkema Van Dijk '17 Will La Dow '18 |
Sarah Placek '18 Taylor Kirkpatrick '20 Kathryn Booker '19 |
|
| University of Hawaii | Rainbows | Chuck Eaton '17 Jeremy Hitchcock '17 Michael Pacholski '19 Patrick Wilkinson '20 |
Annika Garrett '19 Danielle Ahir '20 Cole Brauer '17 |
|
| University of California at Santa Barbara | Gauchos | Christopher Weis '18 Stephen Long '17 Sterling Henken '18 |
Claire Hunt '19 Kristina Miller '17 Ellen Gable '17 Elizabeth Moody '20 |
|
| Cal Poly University S.L.O. | Mustang | Ben Brough '19 Joseph Lausten '18 Liam Hood '20 |
Helen Payne '19 Belle Lemoine '19 Alyson Crowley '20 |
|
| University of California at Berkeley | Bears | Andrew Solomon '18 Eric Witte '17 Ian Markowitz '17 |
Ekaterina Goncharova '18 Kylie Fawcett '20 Megan Grosspietsch '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 ±0.09 means a rating gap counts about 8% 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.