insights
Does the projection ordering hold up?
Projection ordering carries information well beyond the top-ranked players. Evidence varies by statistic, season and rank region, and many shallower-region negatives are inconclusive because the available data cannot resolve the preregistered practical effect.
Points, Goals and Shots on Goal are three separately preregistered surfaces, reported independently. They are not combined, ranked against each other, or summarised into one score.
| Season | 1-25 | 26-50 | 51-100 | 101-200 | 201-350 | 351-550 | 551+ |
|---|---|---|---|---|---|---|---|
| 2021–22 | Ordering evidence | Ordering evidence | Inconclusive | Ordering evidence | No ordering evidence | No ordering evidence | Ordering evidence |
| 2022–23 | Inconclusive | Inconclusive | Ordering evidence | Ordering evidence | Evidence, below threshold | Ordering evidence | Inconclusive |
| 2023–24 | Ordering evidence | Inconclusive | Inconclusive | Ordering evidence | Evidence, below threshold | Ordering evidence | Ordering evidence |
| 2024–25 | Inconclusive | Inconclusive | Ordering evidence | Ordering evidence | Ordering evidence | Evidence, below threshold | Inconclusive |
| 2025–26 | Inconclusive | Ordering evidence | Inconclusive | Ordering evidence | No ordering evidence | Evidence, below threshold | Ordering evidence |
Ordering evidenceEvidence, below thresholdInverted orderingInverted, below thresholdNo ordering evidenceInconclusive — the design could not have told
Full statistical results
Every cell above, with the figure behind it: s, its 95% interval, and whether the region could have resolved the preregistered effect at all. “How to read a cell” is below the table.
| Season | Ranks 1-25 | Ranks 26-50 | Ranks 51-100 | Ranks 101-200 | Ranks 201-350 | Ranks 351-550 | Ranks 551+ |
|---|---|---|---|---|---|---|---|
| 2021–22 | Ordering evidence s 0.606 95% interval 0.476–0.712 ◇ not resolvable | Ordering evidence s 0.624 95% interval 0.541–0.704 ◇ not resolvable | Inconclusive s 0.541 95% interval 0.479–0.600 ◇ not resolvable | Ordering evidence s 0.577 95% interval 0.533–0.617 ◆ resolvable | No ordering evidence s 0.530 95% interval 0.498–0.563 ◆ resolvable | No ordering evidence s 0.523 95% interval 0.494–0.552 ◆ resolvable | Ordering evidence s 0.583 95% interval 0.526–0.636 ◇ not resolvable |
| 2022–23 | Inconclusive s 0.586 95% interval 0.474–0.691 ◇ not resolvable | Inconclusive s 0.561 95% interval 0.477–0.636 ◇ not resolvable | Ordering evidence s 0.571 95% interval 0.510–0.631 ◇ not resolvable | Ordering evidence s 0.578 95% interval 0.538–0.619 ◆ resolvable | Evidence, below threshold s 0.545 95% interval 0.509–0.580 ◆ resolvable | Ordering evidence s 0.565 95% interval 0.534–0.594 ◆ resolvable | Inconclusive s 0.534 95% interval 0.457–0.613 ◇ not resolvable |
| 2023–24 | Ordering evidence s 0.646 95% interval 0.533–0.749 ◇ not resolvable | Inconclusive s 0.448 95% interval 0.357–0.550 ◇ not resolvable | Inconclusive s 0.536 95% interval 0.469–0.603 ◇ not resolvable | Ordering evidence s 0.572 95% interval 0.534–0.610 ◆ resolvable | Evidence, below threshold s 0.541 95% interval 0.506–0.576 ◆ resolvable | Ordering evidence s 0.569 95% interval 0.541–0.597 ◆ resolvable | Ordering evidence s 0.588 95% interval 0.511–0.666 ◇ not resolvable |
| 2024–25 | Inconclusive s 0.607 95% interval 0.500–0.716 ◇ not resolvable | Inconclusive s 0.518 95% interval 0.430–0.610 ◇ not resolvable | Ordering evidence s 0.575 95% interval 0.517–0.630 ◇ not resolvable | Ordering evidence s 0.595 95% interval 0.559–0.634 ◆ resolvable | Ordering evidence s 0.558 95% interval 0.523–0.589 ◆ resolvable | Evidence, below threshold s 0.545 95% interval 0.517–0.573 ◆ resolvable | Inconclusive s 0.552 95% interval 0.475–0.631 ◇ not resolvable |
| 2025–26 | Inconclusive s 0.504 95% interval 0.417–0.595 ◇ not resolvable | Ordering evidence s 0.619 95% interval 0.519–0.717 ◇ not resolvable | Inconclusive s 0.556 95% interval 0.494–0.615 ◇ not resolvable | Ordering evidence s 0.552 95% interval 0.511–0.591 ◆ resolvable | No ordering evidence s 0.533 95% interval 0.500–0.564 ◆ resolvable | Evidence, below threshold s 0.541 95% interval 0.510–0.572 ◆ resolvable | Ordering evidence s 0.585 95% interval 0.517–0.650 ◇ not resolvable |
How to read a cell
- s
- The share of correctly ordered player pairs, aggregated equally over three in-season cutoffs. 0.5 is the value a shuffled board would produce.
- 95% interval
- Uncertainty around the observed s. It says how precisely s is estimated — it is not a significance test and played no part in the verdict.
- The verdict
- Comes from comparing sagainst that region’s own shuffled-board range — a separate quantity from the interval above, answering is this distinguishable from no ordering at all?
- ◇ not resolvable, and why “inconclusive” is not a negative
- Some regions carry too few comparisons for the method to detect an effect of the size declared in advance, even if one existed. There, a non-finding is reported as inconclusive — meaning the design could not have told. It does not mean the ordering failed.
Five seasons, three preregistered statistics, seven rank regions. Method and thresholds were fixed before the data was computed. Computed at revision 44ddb299004f.