If you wanted to predict the javelin qualifying mark and deselect athletes on it, does any method work?
Three methods - current form, average of the last four editions, last time's mark - tested against ten editions of the men's European Championships javelin (2002-2026).
No method predicts the javelin qualifying mark well enough to deselect on. Tested against the past, the best is typically out by 1.3m - more than most senior throwers improve in a year - and the mark actually needed ranged by 4.0m. Ranking the field on current form over-predicted in all 10 editions, by 2.17m on average, and picked only 67% of the actual finalists.
What it means for selection: a predicted qualifying mark is little better than a guess. Nobody should be deselected on a guess.
Scope of data used in this analysis:
A, current form: rank the athletes who actually competed by the average of their top five throws in the 53 weeks to one week before, and take the 12th. (It even gets to know who turned up.)
B, history: average the qualifying mark from the previous four editions.
C, last time: repeat the previous edition's mark.
Live-queried - see "Methodology" below for how these figures are derived.
| Year | Venue | Actual mark to reach final | Field size | Top-5 avg prediction | Delta | % predicted top 12 who qualified | 4-prev-editions prediction | Delta | Last-time prediction | Delta |
|---|---|---|---|---|---|---|---|---|---|---|
| 2002 | München | 79.04 | 26 | 82.87 | +3.83 | 83.3% | - | - | - | - |
| 2006 | Göteborg | 79.24 | 24 | 80.76 | +1.52 | 83.3% | 79.04 | -0.20 | 79.04 | -0.20 |
| 2010 | Barcelona | 76.69 | 23 | 80.66 | +3.97 | 66.7% | 79.14 | +2.45 | 79.24 | +2.55 |
| 2012 | Helsinki | 78.89 | 29 | 80.49 | +1.60 | 58.3% | 78.32 | -0.57 | 76.69 | -2.20 |
| 2014 | Zürich | 78.22 | 32 | 81.32 | +3.10 | 58.3% | 78.47 | +0.25 | 78.89 | +0.67 |
| 2016 | Amsterdam | 80.70 | 31 | 81.92 | +1.22 | 50.0% | 78.26 | -2.44 | 78.22 | -2.48 |
| 2018 | Berlin | 79.74 | 28 | 81.27 | +1.53 | 75.0% | 78.63 | -1.11 | 80.70 | +0.96 |
| 2022 | München | 77.20 | 24 | 80.80 | +3.60 | 66.7% | 79.39 | +2.19 | 79.74 | +2.54 |
| 2024 | Roma | 80.52 | 30 | 80.66 | +0.14 | 66.7% | 78.97 | -1.55 | 77.20 | -3.32 |
| 2026 | Birmingham | 78.88 | 30 | 80.02 | +1.14 | 58.3% | 79.54 | +0.66 | 80.52 | +1.64 |
Delta = prediction minus actual mark. Positive (red) means the method over-predicted the mark required; negative (blue) means it under-predicted. All three delta columns are coloured on the same scale, centred on zero, so the depth of colour is comparable between methods. 2002 has no 4-prev-editions or last-time figure since this dataset starts there.
Computed from the per-edition table above, not stored separately.
| Top-5 average | 4-previous-editions | Last time | |
|---|---|---|---|
| Editions tested | 10 | 9 | 9 |
| Mean error | +2.17m | -0.04m | +0.02m |
| Mean absolute error | 2.17m | 1.27m | 1.84m |
| RMSE | 2.51m | 1.54m | 2.08m |
| Over-predictions | 10 of 10 | 4 of 9 | 5 of 9 |
| Largest error | +3.97m | +2.45m | -3.32m |
Actual mark required across 10 editions: mean 78.91m, SD 1.29m, range 76.69m to 80.70m. Across the same editions, an average of 66.7% of the twelve athletes predicted by the form-based method actually went on to qualify for the final.
Solid black line is the actual mark required. Dashed red is the top-5 form-based prediction. Dashed blue is the 4-previous-editions prediction, with a shaded band of plus or minus the 4-prev method's own RMSE (1.54m) around it, to show the forecast uncertainty rather than a single deceptively precise line. Dashed green is the last-time prediction - simply the previous edition's actual mark, carried forward one edition at a time.
This page is live-queried against the results tables this site already loads, cached for up to 7 days like the other analysis pages, using the same schema and conventions throughout.
Actual mark to reach final / Field size - the smallest qualifying-round
mark among athletes who went on to compete in the final, and the number of distinct
athletes in the qualifying round, for each European Championships men's javelin
competition. Qualifying-round results are identified by race = 'Qualification -
Group', confirmed consistent across all editions of source data (2026-08-20).
Method A, top-5 form average - for each competition, take every throw by every athlete in that competition's qualifying-round field, in the 53 weeks ending one week before the championship started; average each athlete's own best five throws in that window; rank the field by that average; the 12th-ranked athlete's average is the predicted mark. Depends on full-field javelin results coverage (not just GB/EU/medallist athletes), confirmed at 100% across all ten editions as of 2026-08-20.
"% predicted top 12 who qualified" compares the 12 athletes ranked highest by that average against the athletes who actually appear in that competition's Final race, and reports the overlap as a percentage of 12.
Method B, 4-previous-editions average - simply the mean of the actual mark required (from the method above) at the four most recent prior editions of the championship.
Method C, last time - the actual mark required (from the method above) at the single most recent prior edition of the championship, with no averaging.