How well priced is the closing line?
Every other measurement here asks whether a model can beat the market. This asks the inverted question, which needs no model at all: given the closing prices and what actually happened, how well priced was the line?
On shots on goal the Pinnacle close was measurably mis-priced in two consecutive seasons and calibrated in the third. Betting that mispricing loses in every season measured — the error is about three points and the margin charged for the bet is about seven, so there is nothing left to take. Both halves are the finding. Neither is usable on its own.
Each market and season is reported separately and never pooled. A figure blended across seasons is not a coarser answer to this question; it is an answer to a different one.
Was the close calibrated?
The gap is the mean de-vigged probability the market implied, minus what actually happened. Positive means the Over was priced too dear. An interval containing zero means no directional mispricing is detectable.
| Market | Season | Prices | Games | Hold | Implied | Realized | Gap | 95% interval | Reading |
|---|---|---|---|---|---|---|---|---|---|
| shots on goal | 2023–24 | 6,920 | 499 | 7.12% | 0.5102 | 0.4788 | +0.0315 | [+0.0203, +0.0432] | Over priced too dear |
| shots on goal | 2024–25 | 6,920 | 498 | 7.21% | 0.5090 | 0.4790 | +0.0300 | [+0.0177, +0.0427] | Over priced too dear |
| shots on goal | 2025–26 | 8,349 | 565 | 7.03% | 0.5079 | 0.5023 | +0.0056 | [−0.0053, +0.0170] | No detectable mispricing |
| points | 2025–26 | 8,601 | 497 | 7.03% | 0.4621 | 0.4680 | −0.0058 | [−0.0194, +0.0081] | No detectable mispricing |
| assists | 2025–26 | 8,556 | 497 | 7.03% | 0.3417 | 0.3394 | +0.0023 | [−0.0097, +0.0141] | No detectable mispricing |
| anytime goal | 2025–26 | 7,821 | 597 | 7.07% | 0.2600 | 0.2590 | +0.0010 | [−0.0079, +0.0103] | No detectable mispricing |
Does the mispricing clear the hold?
A gap is not an edge. The cheapest rule that exploits a positive gap is to bet Under on everything — no model, no selection, no timing — so it is the ceiling for “just bet the mispricing”. Where it still loses, the error was smaller than the margin and there was nothing to take.
| Market | Season | Bets | Win rate | Return / unit | 95% interval | Hold | Reading |
|---|---|---|---|---|---|---|---|
| shots on goal | 2023–24 | 6,920 | 52.12% | −0.0049 | [−0.0273, +0.0181] | 7.12% | Sub-vig |
| shots on goal | 2024–25 | 6,920 | 52.10% | −0.0079 | [−0.0322, +0.0165] | 7.21% | Sub-vig |
| shots on goal | 2025–26 | 8,349 | 49.77% | −0.0555 | [−0.0765, −0.0335] | 7.03% | Sub-vig |
| points | 2025–26 | 8,601 | 53.20% | −0.0728 | [−0.0986, −0.0465] | 7.03% | Sub-vig |
| assists | 2025–26 | 8,556 | 66.06% | −0.0604 | [−0.0789, −0.0422] | 7.03% | Sub-vig |
| anytime goal | 2025–26 | 7,821 | 74.10% | −0.0635 | [−0.0755, −0.0513] | 7.07% | Sub-vig |
Every return above is negative, and in the two mis-priced shots seasons the interval still contains zero — so the honest reading there is not distinguishable from break-even rather than a measured loss. That is not a rescue. An error you cannot tell from zero, inside a seven-point margin, is not something to bet either.
Right on average, wrong in the tails?
The same comparison within equal-count bins of implied probability, against a null of a market that is exactly right: outcomes redrawn from the market’s own prices, binned identically, 1,000 draws.
| Market | Season | Bins leaning over | Worst bin | Null p95 | p | Reading |
|---|---|---|---|---|---|---|
| shots on goal | 2023–24 | 10 of 10 | 0.0593 | 0.0522 | 0.015 | Beyond its own null |
| shots on goal | 2024–25 | 9 of 10 | 0.0477 | 0.0538 | 0.105 | Consistent with noise |
| shots on goal | 2025–26 | 7 of 10 | 0.0504 | 0.0478 | 0.036 | Beyond its own null |
| points | 2025–26 | 2 of 10 | 0.0315 | 0.0472 | 0.433 | Consistent with noise |
| assists | 2025–26 | 6 of 10 | 0.0239 | 0.0452 | 0.767 | Consistent with noise |
| anytime goal | 2025–26 | 6 of 10 | 0.0326 | 0.0451 | 0.320 | Consistent with noise |
Read the two right-hand columns as the weakest numbers here. The worst bin is an extremum over ten, and its p-value has already flipped one published verdict when the sample grew by 5.7% — while the headline gap barely moved. What replicates is the left-hand column: the bins lean one way almost uniformly in the mis-priced seasons, which is a level shift across the whole range rather than a tilt at one end. A favourite-longshot bias would have to sit at the same end twice, and it does not.
What this does and does not say
- Closing lines only.
- One snapshot per game, player and market. Nothing here says anything about how lines move during the day; that has never been captured.
- The de-vig is a lever.
- Probabilities are stripped of margin proportionally. Other methods redistribute it differently, and a favourite-longshot effect would appear partly as an artefact of that choice, which is why the hold is shown beside every row.
- Not a recommendation.
- The Under rule is measured as a ceiling on exploiting the gap, not offered as a strategy. It loses in every market and season here.
- The frame grows.
- These figures are joined to captured odds and move whenever a new capture lands. They are re-derived by a job, not maintained by hand.
Computed at revision 63d01fbd8ebd.