| # | School | Team | Rec. | |
|---|---|---|---|---|
| 1 |  |
Roger Williams University | Hawks | 8–2 |
| 2 |  |
Fordham University | Rams | 7–3 |
| 3 |  |
Connecticut College | Camels | 6–4 |
| 4 |  |
Yale University | Bulldogs | 5–5 |
| 5 |  |
Tufts University | Jumbos | 2–8 |
| 6 |  |
Dartmouth College | Big Green | 2–8 |
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 8,592 team race matches sailed before 2017-04-02, using the line-ups that actually raced. It called 18 of 30 matches (60%) with a log-loss of 0.815 (a coin flip scores 0.693), so the event went poorly for the forecast. Orderliness −1.22 ± 0.42: an upset-heavy event, more orderly than 1% 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 | Fordham University | 7.75 | 10.14 | 7–3 | 1.8 | +2.39 | 9.5 | <1% |
| 1 | Roger Williams University | 9.47 | 10.40 | 8–2 | 6.2 | +0.93 | 1.1 | 20% |
| 4 | Yale University | 9.11 | 9.25 | 5–5 | 4.7 | +0.14 | 0.0 | 56% |
| 3 | Connecticut College | 10.18 | 9.34 | 6–4 | 7.6 | −0.84 | 1.0 | 94% |
| 6 | Dartmouth College | 9.07 | 7.62 | 2–8 | 4.6 | −1.44 | 2.5 | 99% |
| 5 | Tufts University | 9.17 | 7.55 | 2–8 | 5.1 | −1.62 | 3.3 | 99% |
| Skipper | School | Value | Perf. | Record | Exp. wins | Δ | Surprise (bits) | P(this good or better) |
|---|---|---|---|---|---|---|---|---|
| Anders Ekholm | Fordham University | 2.37 | 4.76 | 7–3 | 1.8 | +2.39 | 9.5 | <1% |
| Michael Gemperline | Roger Williams University | 3.13 | 4.06 | 8–2 | 6.2 | +0.93 | 1.1 | 20% |
| Conner Harding | Roger Williams University | 3.54 | 4.47 | 8–2 | 6.2 | +0.93 | 1.1 | 20% |
| Ed Lebens | Roger Williams University | 2.67 | 3.60 | 8–2 | 6.2 | +0.93 | 1.1 | 20% |
| Christopher Champa | Yale University | 2.27 | 2.41 | 5–5 | 4.7 | +0.14 | 0.0 | 56% |
| Cooper Nefsky | Connecticut College | 2.36 | 1.40 | 3–3 | 4.2 | −0.97 | 0.9 | 94% |
| Walter Florio | Connecticut College | 2.96 | 1.60 | 4–4 | 6.1 | −1.36 | 2.2 | 99% |
| Chris Keller | Tufts University | 2.72 | 1.10 | 2–8 | 5.1 | −1.62 | 3.3 | 99% |
| James Beatty | Tufts University | 3.13 | 1.51 | 2–8 | 5.1 | −1.62 | 3.3 | 99% |
Probability the model gave the side that went on to win. Red bars are upsets (the winner was given under 50%).
| Team | Rec. | Hawks | Rams | Camels | Bulldogs | Jumbos | Green | |
|---|---|---|---|---|---|---|---|---|
| Roger Williams University Hawks | 5–0 | ✕ | W | W | W | W | W |
| Fordham University Rams | 3–2 | L | ✕ | W | L | W | W |
| Connecticut College Camels | 3–2 | L | L | ✕ | W | W | W |
| Yale University Bulldogs | 2–3 | L | W | L | ✕ | W | L |
| Tufts University Jumbos | 1–4 | L | L | L | L | ✕ | W |
| Dartmouth College Big Green | 1–4 | L | L | L | W | L | ✕ |
| Team | Rec. | Hawks | Rams | Camels | Bulldogs | Jumbos | Green | |
|---|---|---|---|---|---|---|---|---|
| Roger Williams University Hawks | 3–2 | ✕ | L | L | W | W | W |
| Fordham University Rams | 4–1 | W | ✕ | W | L | W | W |
| Connecticut College Camels | 3–2 | W | L | ✕ | W | W | L |
| Yale University Bulldogs | 3–2 | L | W | L | ✕ | W | W |
| Tufts University Jumbos | 1–4 | L | L | L | L | ✕ | W |
| Dartmouth College Big Green | 1–4 | L | L | W | L | L | ✕ |
| # | Winner | Loser | Pos. | ||||
|---|---|---|---|---|---|---|---|
| 1 | |
Hawks | 1-2-4 | def. | |
Rams | 3-5-6 |
| 2 | |
Jumbos | 2-3-4 | def. | |
Big Green | 1-5-6 |
| 3 | |
Camels | 1-2-3 | def. | |
Bulldogs | 4-5-6 |
| 4 | |
Rams | 1-2-3 | def. | |
Big Green | 4-5-6 |
| 5 | |
Hawks | 2-3-4 | def. | |
Bulldogs | 1-5-6 |
| 6 | |
Camels | 1-2-4 | def. | |
Jumbos | 3-5-6 |
| 7 | |
Big Green | 1-2-4 | def. | |
Bulldogs | 3-5-6 |
| 8 | |
Rams | 2-3-4 | def. | |
Jumbos | 1-5-6 |
| 9 | |
Hawks | 1-3-6 | def. | |
Camels | 2-4-5 |
| 10 | |
Bulldogs | 1-2-3 | def. | |
Jumbos | 4-5-6 |
| 11 | |
Hawks | 2-3-4 | def. | |
Big Green | 1-5-6 |
| 12 | |
Rams | 1-2-5 | def. | |
Camels | 3-4-6 |
| 13 | |
Hawks | 2-3-4 | def. | |
Jumbos | 1-5-6 |
| 14 | |
Bulldogs | 1-3-6 | def. | |
Rams | 2-4-5 |
| 15 | |
Camels | 1-2-5 | def. | |
Big Green | 3-4-6 |
| 16 | |
Rams | 1-3-5 | def. | |
Hawks | 2-4-6 |
| 17 | |
Jumbos | 1-2-5 | def. | |
Big Green | 3-4-6 |
| 18 | |
Camels | 1-2-6 | def. | |
Bulldogs | 3-4-5 |
| 19 | |
Rams | 2-3-4 | def. | |
Big Green | 1-5-6 |
| 20 | |
Hawks | 2-3-4 | def. | |
Bulldogs | 1-5-6 |
| 21 | |
Camels | 1-2-5 | def. | |
Jumbos | 3-4-6 |
| 22 | |
Bulldogs | 2-3-4 | def. | |
Big Green | 1-5-6 |
| 23 | |
Rams | 1-2-4 | def. | |
Jumbos | 3-5-6 |
| 24 | |
Camels | 2-3-5 | def. | |
Hawks | 1-4-6 |
| 25 | |
Bulldogs | 1-2-3 | def. | |
Jumbos | 4-5-6 |
| 26 | |
Hawks | 1-2-4 | def. | |
Big Green | 3-5-6 |
| 27 | |
Rams | 1-2-5 | def. | |
Camels | 3-4-6 |
| 28 | |
Hawks | 1-2-3 | def. | |
Jumbos | 4-5-6 |
| 29 | |
Bulldogs | 1-3-4 | def. | |
Rams | 2-5-6 |
| 30 | |
Big Green | 1-3-5 | def. | |
Camels | 2-4-6 |
| School | Team | Skippers | Crew | |
|---|---|---|---|---|
|
Roger Williams University | Hawks | Conner Harding '19 Ed Lebens '19 Michael Gemperline '17 |
Hallie Repeta '19 Brigette Croke '17 Beatrice Bellacosa '17 Megan Roach '18 |
|
Fordham University | Rams | Anders Ekholm '17 Brad Seferian '19 Tucker Hersam '20 |
Emma Archard '18 Cortney Rielly '20 Jamie Spence '18 |
|
Connecticut College | Camels | Carter Pemberton '20 Cooper Nefsky '17 Hugh Macgillivray '18 Walter Florio '18 |
Albert Rodiger '18 Austin Smith '20 Eliza Garry '17 Erin Smith '19 |
|
Yale University | Bulldogs | Christine Klingler '20 Christopher Champa '18 Louisa Nordstrom '20 |
Kira Woods '19 Caroline Colwell '18 Charles Skoda '17 |
|
Tufts University | Jumbos | Chris Keller '19 Jack Bitney '19 James Beatty '17 |
Taylor Hart '19 Natalie Danziger '17 Caroline Ambros '17 |
|
Dartmouth College | Big Green | Erik Weis '18 Jack Mcgraw '20 Noah Simmons '20 |
Alyssa Berger '19 Mary Amis '19 James Bonham '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 ±0.08 means a rating gap counts about 7% 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.
