| # | School | Team | Rec. | |
|---|---|---|---|---|
| 1 |  |
Broadneck High School | Bruins | 7–0 |
| 2 |  |
Archbishop Spalding | Cavaliers | 5–2 |
| 3 |  |
Key School | Zags | 3–4 |
| 4 |  |
St. Mary's High School (MD) | Saints | 3–4 |
| 5 |  |
Sts. Peter & Paul | Sabres | 3–4 |
| 6 |  |
Annapolis High School | Panthers | 3–4 |
| 7 |  |
Edmund Burke School | Bengals | 2–5 |
| 8 |  |
Severna Park | Falcons | 2–5 |
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 2,651 team race matches sailed before 2017-03-12, using the line-ups that actually raced. It called 22 of 28 matches (79%) with a log-loss of 0.709 (a coin flip scores 0.693), so the event went poorly for the forecast. Orderliness −1.38 ± 0.45: an upset-heavy event, more orderly than 4% of high school 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) |
|---|---|---|---|---|---|---|---|---|
| 5 | Sts. Peter & Paul | 1.88 | 4.91 | 3–4 | 0.6 | +3.03 | 4.8 | 1% |
| 1 | Broadneck High School | 6.48 | 9.48 | 7–0 | 5.3 | ≥+3.00 | 2.7 | 12% |
| 3 | Key School | 3.71 | 4.77 | 3–4 | 2.0 | +1.06 | 0.6 | 29% |
| 2 | Archbishop Spalding | 6.27 | 6.22 | 5–2 | 5.1 | −0.05 | 0.0 | 70% |
| 8 | Severna Park | 4.47 | 3.55 | 2–5 | 2.9 | −0.93 | 0.4 | 89% |
| 4 | St. Mary's High School (MD) | 5.61 | 4.36 | 3–4 | 4.3 | −1.25 | 0.9 | 94% |
| 6 | Annapolis High School | 5.74 | 4.44 | 3–4 | 4.4 | −1.30 | 1.0 | 95% |
| 7 | Edmund Burke School | 5.08 | 3.48 | 2–5 | 3.5 | −1.60 | 1.3 | 97% |
| Skipper | School | Value | Perf. | Record | Exp. wins | Δ | Surprise (bits) | P(this good or better) |
|---|---|---|---|---|---|---|---|---|
| Sunny Sturmer | Sts. Peter & Paul | 0.35 | 3.38 | 3–4 | 0.6 | +3.03 | 4.8 | 1% |
| Noah Kullman | Sts. Peter & Paul | 0.59 | 3.62 | 3–4 | 0.6 | +3.03 | 4.8 | 1% |
| Coleman Walker | Sts. Peter & Paul | 0.68 | 3.71 | 3–4 | 0.6 | +3.03 | 4.8 | 1% |
| Nicole Ryan | Broadneck High School | 1.11 | 4.11 | 7–0 | 5.3 | ≥+3.00 | 2.7 | 12% |
| Kate Riley | Severna Park | 1.60 | 1.89 | 2–3 | 1.8 | +0.29 | 0.0 | 59% |
| Jack Irvin | Archbishop Spalding | 1.46 | 1.40 | 5–2 | 5.1 | −0.05 | 0.0 | 70% |
| Ian Mathiesen | Severna Park | 1.69 | 0.76 | 2–5 | 2.9 | −0.93 | 0.4 | 89% |
| James Golden | St. Mary's High School (MD) | 1.95 | 0.71 | 3–4 | 4.3 | −1.25 | 0.9 | 94% |
| George Kaye | Annapolis High School | 1.68 | 0.38 | 3–4 | 4.4 | −1.30 | 1.0 | 95% |
| Remington King | Annapolis High School | 2.05 | 0.75 | 3–4 | 4.4 | −1.30 | 1.0 | 95% |
Probability the model gave the side that went on to win. Red bars are upsets (the winner was given under 50%).
| # | Winner | Loser | Pos. | ||||
|---|---|---|---|---|---|---|---|
| 1 | |
Bengals | 1-4-5 | def. | |
Zags | 2-3-6 |
| 2 | |
Bruins | 1-2-3 | def. | |
Sabres | 4-5-6 |
| 3 | |
Falcons | 1-3-5 | def. | |
Cavaliers | 2-4-6 |
| 4 | |
Panthers | 1-2-6 | def. | |
Saints | 3-4-5 |
| 5 | |
Bruins | 1-2-4 | def. | |
Bengals | 3-5-6 |
| 6 | |
Cavaliers | 1-2-6 | def. | |
Zags | 3-4-5 |
| 7 | |
Saints | 1-2-3 | def. | |
Sabres | 4-5-6 |
| 8 | |
Panthers | 1-4-5 | def. | |
Falcons | 2-3-6 |
| 9 | |
Bruins | 1-3-4 | def. | |
Cavaliers | 2-5-6 |
| 10 | |
Saints | 1-4-6 BKD | def. | |
Bengals | 2-3-5 |
| 11 | |
Falcons | 1-2-4 | def. | |
Zags | 3-5-6 |
| 12 | |
Sabres | 1-2-4 | def. | |
Panthers | 3-5-6 |
| 13 | |
Cavaliers | 1-3-5 | def. | |
Saints | 2-4-6 |
| 14 | |
Bruins | 2-3-5 | def. | |
Falcons | 1-4-6 |
| 15 | |
Sabres | 1-2-6 | def. | |
Bengals | 3-4-5 |
| 16 | |
Zags | 1-2-4 | def. | |
Panthers | 3-5-6 |
| 17 | |
Saints | 1-4-5 | def. | |
Falcons | 2-3-6 |
| 18 | |
Cavaliers | 1-3-4 | def. | |
Sabres | 2-5-6 |
| 19 | |
Bruins | 1-4-5 | def. | |
Zags | 2-3-6 |
| 20 | |
Panthers | 1-4-5 | def. | |
Bengals | 2-3-6 |
| 21 | |
Sabres | 1-3-4 | def. | |
Falcons | 2-5-6 |
| 22 | |
Zags | 1-2-5 | def. | |
Saints | 3-4-6 |
| 23 | |
Cavaliers | 1-2-3 | def. | |
Bengals | 4-5-6 |
| 24 | |
Bruins | 2-3-4 | def. | |
Panthers | 1-5-6 |
| 25 | |
Zags | 1-2-4 | def. | |
Sabres | 3-5-6 |
| 26 | |
Bengals | 1-4-5 | def. | |
Falcons | 2-3-6 |
| 27 | |
Bruins | 2-3-4 | def. | |
Saints | 1-5-6 |
| 28 | |
Cavaliers | 2-3-4 | def. | |
Panthers | 1-5-6 |
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 ±0.01 means a rating gap counts about 1% 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.
